biondizzle/DeepGEMM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
deff80c9c1e02d839d1a513130e65d13c5f5e6a1
DeepGEMM/deep_gemm/mega
History
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
..
__init__.py
fix: add Python wrapper for NVFP4 SymmBuffer allocation
2026-05-11 08:05:21 +00:00