Separate source and destination FP4 scale packing in requant_fp4_to_gran_k so group16-to-group32 conversion always recomputes UE8M0 runtime scales by default.
Make prepare_fp4_weights_for_mega_moe accept raw grouped FP4 weights and scales, then perform optional requantization, DeepGEMM scale layout transform, and MegaMoE UTCCP weight transform internally.
Update the MegaMoE synthetic benchmark so baseline grouped GEMM uses runtime-layout weights while fused MegaMoE uses transformed weights from the same raw source tensors.
Tested: PYTHONPYCACHEPREFIX=/private/tmp/deepgemm_pycache python3 -m py_compile deep_gemm/__init__.py deep_gemm/mega/__init__.py deep_gemm/utils/math.py tests/test_layout.py tests/test_mega_moe.py
Tested: git diff --check
Not-tested: CUDA build, SM100/B300 runtime, and GLM-5.2 accuracy validation are not available locally.
Add a top-level MegaMoE helper that handles source/runtime FP4 weight granularity before applying the existing MegaMoE weight layout transform.
Use the helper from the synthetic MegaMoE benchmark so SGLang can later follow the same contract for GLM-5.2 NVFP4 group16 checkpoints.
Tested: PYTHONPYCACHEPREFIX=/private/tmp/deepgemm_pycache python3 -m py_compile deep_gemm/__init__.py deep_gemm/mega/__init__.py tests/test_mega_moe.py
Tested: git diff --check
Not-tested: CUDA build, SM100/B300 runtime, and GLM-5.2 accuracy validation are not available locally.
Add a utility and synthetic benchmark path for converting FP4 group16 tensors into group32 tensors that the existing SM100 block32 MegaMoE kernels can consume.
Document that this is a requantization path rather than a lossless metadata rewrite, so GLM-5.2 accuracy validation is still required before production use.
Tested: PYTHONPYCACHEPREFIX=/private/tmp/deepgemm_pycache python3 -m py_compile deep_gemm/utils/math.py tests/test_layout.py tests/test_mega_moe.py
Tested: git diff --check
Not-tested: CUDA build, SM100/B300 runtime, and GLM-5.2 accuracy validation are not available locally.
Allow SM100 FP4 scale layout transforms to accept group16 and thread weight granularity through the MegaMoE Python wrapper, API checks, and synthetic benchmark entrypoint.
Keep fused SM100 MegaMoE compute behind an explicit group16 capability gate until the SFB/TMEM/MMA scale path is updated and validated.
Tested: PYTHONPYCACHEPREFIX=/private/tmp/deepgemm_pycache python3 -m py_compile deep_gemm/mega/__init__.py tests/test_mega_moe.py tests/generators.py
Tested: git diff --check
Not-tested: CUDA build and SM100/B300 runtime validation are not available locally.
The function sm90_bf16_k_grouped_gemm was incorrectly using SM100ArchSpec
to calculate TMA descriptor block sizes. Since this file is the SM90
implementation, it should consistently use SM90ArchSpec like the other
functions in this file (sm90_bf16_gemm, sm90_m_grouped_bf16_gemm_contiguous,
etc.).
This fixes a copy-paste error that could cause incorrect block size
calculations on SM90 (Hopper) GPUs.
Fixes#242🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
