Baichuan-M2-32B-GPTQ-Int4
852
11
32.0B
2 languages
license:apache-2.0
by
baichuan-inc
Language Model
OTHER
32B params
New
852 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
72GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
30GB+ RAM
Code Examples
⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3⚙️ Quick Startbash
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3bashvllm
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16MTP inference with SGLangtext
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.