iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Feature][Humming] Humming feature integration (#56685)

Browse Source 
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Jinzhen Lin
2026-09-20 08:11:01 -07:00
committed by GitHub
co-authored by Codex mgoin
parent 27757dde02
commit 7d99c2c4fd
62 changed files with 2040 additions and 1086 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/kernels/quantization/test_mxfp4_kernel_selection.py
+1 -2
View File
@@ -14,7 +14,6 @@ from vllm.model_executor.kernels.linear import (
AiterMxfp4LinearKernel,
EmulationMxfp4LinearKernel,
FlashInferMxFp4LinearKernel,
HummingMxFp4LinearKernel,
MarlinMxFp4LinearKernel,
MxFp4LinearKernel,
MxFp4LinearLayerConfig,
@@ -44,7 +43,7 @@ _TRUE_W4A4_KERNELS = [
# Weight-only (A16) kernels: they never quantize activations. They still accept
# MXFP4 activation keys as an intentional compatibility fallback.
_WEIGHT_ONLY_KERNELS = [MarlinMxFp4LinearKernel, HummingMxFp4LinearKernel]
_WEIGHT_ONLY_KERNELS = [MarlinMxFp4LinearKernel]
def test_can_implement_is_abstract():