[Quantization] add humming mxfp4 moe backend (#41083)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
This commit is contained in:
@@ -118,6 +118,7 @@ MoEBackend = Literal[
|
||||
"flashinfer_cutlass",
|
||||
"flashinfer_cutedsl",
|
||||
"marlin",
|
||||
"humming",
|
||||
"aiter",
|
||||
"emulation",
|
||||
]
|
||||
@@ -148,6 +149,7 @@ class KernelConfig:
|
||||
- "flashinfer_cutlass": Use FlashInfer with CUTLASS kernels
|
||||
- "flashinfer_cutedsl": Use FlashInfer with CuteDSL kernels (FP4 only)
|
||||
- "marlin": Use Marlin kernels (weight-only quantization)
|
||||
- "humming": Use Humming Mixed Precision kernels
|
||||
- "aiter": Use AMD AITer kernels (ROCm only)
|
||||
- "emulation": use BF16/FP16 GEMM, dequantizing weights and
|
||||
running QDQ on activations.
|
||||
|
||||
Reference in New Issue
Block a user