DeepSeek-Math-V2-int4-AutoRound

3
—
by
INC4AI
Language Model
OTHER
New
3 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Code Examples

How to Usebash
git clone -b 457-ds32 https://github.com/yiliu30/transformers.git
cd transformers && pip install -e .

git clone -b ds-v32 https://github.com/intel/auto-round.git
cd auto-round && pip install .
VLLM Usagebashvllm
# https://docs.vllm.ai/projects/recipes/en/latest/DeepSeek/DeepSeek-V3_2.html#launching-deepseek-v32
pip install git+https://github.com/deepseek-ai/[email protected] --no-build-isolation
git clone https://github.com/vllm-project/vllm.git
cd vllm && git checkout 773d7073a
VLLM_PRECOMPILED_WHEEL_COMMIT=7f42dc20bb2800d09faa72b26f25d54e26f1b694 VLLM_USE_PRECOMPILED=1 pip install --editable .

VLLM_ALLREDUCE_USE_SYMM_MEM=0 NCCL_NVLS_ENABLE=0 VLLM_USE_FUSED_MOE_GROUPED_TOPK=0 \
    vllm serve Intel/DeepSeek-Math-V2-int4-AutoRound \
        --tensor-parallel-size 4 \
        --tokenizer-mode deepseek_v32 \
        --tool-call-parser deepseek_v32 \
        --enable-auto-tool-choice \
        --reasoning-parser deepseek_v3

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.