[Model Runner V2] support qwen35 / mamba hybrid model (#35520)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
This commit is contained in:
@@ -142,7 +142,7 @@ class KernelConfig:
|
||||
"""Backend for MoE expert computation kernels. Available options:
|
||||
|
||||
- "auto": Automatically select the best backend based on model and hardware
|
||||
- "triton": Use Triton-based fused MoE kernels
|
||||
- "triton": Use Triton-based fused MoE kernels
|
||||
- "deep_gemm": Use DeepGEMM kernels (FP8 block-quantized only)
|
||||
- "deep_gemm_mega_moe": Use DeepGEMM mega MoE kernels
|
||||
- "cutlass": Use vLLM CUTLASS kernels
|
||||
|
||||
Reference in New Issue
Block a user