LuminolT 2c7543130b feat(megamoe): expose fp4 weight preparation helper ...

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.

2026-07-08 18:36:40 +08:00

3.6 KiB

Raw Blame History

View Raw