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

[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (#8973)

Browse Source 
Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
This commit is contained in:
ElizaWszola
2024-10-04 20:34:44 +02:00
committed by GitHub
parent 0dcc8cbe5a
commit 05d686432f
23 changed files with 969 additions and 223 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/moe/torch_bindings.cpp
View File

@@ -12,7 +12,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
m.def(
"marlin_gemm_moe(Tensor! a, Tensor! b_q_weights, Tensor! sorted_ids, "
"Tensor! topk_weights, Tensor! topk_ids, Tensor! b_scales, Tensor! "
"g_idx, Tensor! perm, Tensor! workspace, "
"b_zeros, Tensor! g_idx, Tensor! perm, Tensor! workspace, "
"__torch__.torch.classes._core_C.ScalarType b_q_type, int size_m, "
"int size_n, int size_k, bool is_k_full, int num_experts, int topk, "
"int moe_block_size, bool replicate_input, bool apply_weights)"