biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

Browse Source 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
This commit is contained in:
Jinzhen Lin
2025-11-29 23:19:33 +08:00
committed by GitHub
parent fa59fe417f
commit 1656ad3704
46 changed files with 4371 additions and 2240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
csrc/moe/torch_bindings.cpp
View File

@@ -63,16 +63,18 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
m.def(
"moe_wna16_marlin_gemm(Tensor! a, Tensor? c_or_none,"
"Tensor! b_q_weight, Tensor? b_bias_or_none,"
"Tensor! b_scales, Tensor? global_scale, Tensor? "
"Tensor! b_scales, Tensor? a_scales, Tensor? global_scale, Tensor? "
"b_zeros_or_none,"
"Tensor? g_idx_or_none, Tensor? perm_or_none, Tensor! workspace,"
"Tensor sorted_token_ids,"
"Tensor! expert_ids, Tensor! num_tokens_past_padded,"
"Tensor! topk_weights, int moe_block_size, int top_k, "
"bool mul_topk_weights, bool is_ep, int b_q_type_id,"
"bool mul_topk_weights, bool is_ep, int b_type_id,"
"int size_m, int size_n, int size_k,"
"bool is_full_k, bool use_atomic_add,"
"bool use_fp32_reduce, bool is_zp_float) -> Tensor");
"bool use_fp32_reduce, bool is_zp_float,"
"int thread_k, int thread_n, int blocks_per_sm) -> Tensor");
m.def(
"marlin_gemm_moe(Tensor! a, Tensor! b_q_weights, Tensor! sorted_ids, "
"Tensor! topk_weights, Tensor! topk_ids, Tensor! b_scales, Tensor! "