[Usage]: RuntimeError: Only SM100 is supported by FP4 block scale MOE
Open
@laikhtewari is already working on this.
Since Sep 16, 2025.
Low Precision
question
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
System Info
Hello,
Is it planned to support SM120 (RTX 6000 PRO) TRTLLM moe backend? CUTLASS backend is working. Second question - should we expect faster inference for NVFP4 on SM120 ? Currently it is not any faster compared to FP8 sglang.
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.
Assessment
This issue has not been assessed yet.