NVIDIA / NVIDIA/Model-Optimizer
[Feature Request] DeepSeek-V4-Flash-0731 NVFP4 checkpoint
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 604
- Avg merge
- 2d 8h
- Merged PRs (30d)
- 142
Description
Detailed description of the requested feature
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash. It's very valuable to have NVFP4 checkpoint to use less computer resources with more tokens output for Blackwell GPU.
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 by reviewing the DeepSeek-V4-Flash-0731 checkpoint at the linked Hugging Face page and search the Model-Optimizer repository for existing NVFP4 checkpoint support. Determine the integration entry point and validation approach for Blackwell GPUs. Done means the requested checkpoint is available in NVFP4 form and works with the project's supported optimization flow.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100