Problem serving nvidia/DeepSeek-V3-0324-FP4 on 8xH200
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
Hi,
I'm trying to deploy huggingface nvidia/DeepSeek-V3-0324-FP4 on 8xH200 server. Both trtllm-serve, vLLM, and sglang are not able to serve this model because of the GPU arch not support this model.
I noticed that the supported device in README of huggingface is:
Inference:
Engine: TensorRT-LLM
Test Hardware: B200
So, my questions is:
- how could I run this model on NVIDIA H200?
- If not, is there any document that I can convert model of deepseek v3 0324 myself to run FP4 on H200?
Thank you!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the Hugging Face model README and the trtllm-serve, vLLM, and sglang entry points mentioned in the report, checking their GPU architecture and FP4 support for H200. Done would require a confirmed way to serve the model on 8xH200 or documentation of a working conversion path, including any limitations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100