KAT-V1-40B-GPTQ-Int4-Int8Mix

3
40.0B
—
by
QuantTrio
Language Model
OTHER
40B params
New
3 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
90GB+ RAM
Mobile
Laptop
Server
Quick Summary

KAT-V1-40B-GPTQ-Int4-Int8Mix Base model Kwaipilot/KAT-V1-40B | File Size | Last Updated | |--------|--------------| | `25GB` | `2025-07-31` | - Kwaipilot-Auto...

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
38GB+ RAM

Code Examples

KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000
KAT-V1-40B-GPTQ-Int4-Int8Mixtextvllm
CONTEXT_LENGTH=32768

vllm serve \
    QuantTrio/KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --served-model-name KAT-V1-40B-GPTQ-Int4-Int8Mix \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.