@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
blas_gemm.h
bmm.cpp
common.h
compressor.cpp
conv.cpp
conv_arm.h
decode.cpp
extend.cpp
fla.cpp
flash_attn.h
flash_mla.cpp
gemm.cpp
gemm.h
gemm_fp8.cpp
gemm_fp8_w8a8.cpp
gemm_int4.cpp
gemm_int8.cpp
indexer.cpp
mhc.cpp
mla_cache.cpp
moe.cpp
moe.h
moe_fp8.cpp
moe_fp8_w8a8.cpp
moe_int4.cpp
moe_int8.cpp
paged_mqa_logits.cpp
store_cache.cpp
topk.cpp
vec.h
vec_pack.h