Skip to content

Conversation

@neurusL
Copy link
Contributor

@neurusL neurusL commented Sep 17, 2025

in tvm/python/tvm/relax/backend/cuda/flashinfer.py added a gen_grouped_gemm_module
in tvm/tests/python/relax/test_group_gemm_flashinfer.py added tests for different combinations of

  • input and output types: ("float8_e4m3fn", "float8_e4m3fn", "bfloat16"), ("float8_e4m3fn", "float8_e4m3fn", "float16"),
  • scale granularity of m, n, k: (1, 128, 128),
  • scale major mode: "MN", "K"
  • mma_sm: 1, 2
  • different batch sizes and m_sizes

Bumps [form-data](https://github.com/form-data/form-data) from 3.0.1 to 3.0.4.
- [Release notes](https://github.com/form-data/form-data/releases)
- [Changelog](https://github.com/form-data/form-data/blob/v3.0.4/CHANGELOG.md)
- [Commits](form-data/form-data@v3.0.1...v3.0.4)

---
updated-dependencies:
- dependency-name: form-data
  dependency-version: 3.0.4
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
@neurusL neurusL closed this Sep 17, 2025
@neurusL neurusL reopened this Sep 17, 2025
@MasterJH5574 MasterJH5574 self-assigned this Sep 17, 2025
@neurusL neurusL force-pushed the feature/flashinfer-grouped_gemm branch from 95ebb87 to 856af7c Compare September 19, 2025 17:05
@neurusL neurusL closed this Sep 19, 2025
@neurusL neurusL deleted the feature/flashinfer-grouped_gemm branch September 19, 2025 19:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants