Files
DeepGEMM/deep_gemm/mega
biondizzle deff80c9c1 fix: add Python wrapper for NVFP4 SymmBuffer allocation
get_symm_buffer_for_nvfp4_mega_moe uses _C.get_symm_buffer_size_for_nvfp4_mega_moe
to allocate the correct buffer size (2x SF entries due to group_size=16).
Custom init to avoid SymmBuffer's hardcoded MXFP4 allocation.
2026-05-11 08:05:21 +00:00
..