vllm/model_executor/layers/fused_moe · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

configs

experts

oracle

prepare_finalize

router

runner

__init__.py

activation.py

all2all_utils.py

b12x.py

config.py

deep_gemm_utils.py

eep_reconfigure.py

expert_map_manager.py

fused_flydsl_moe.py

fused_moe.py

fused_moe_method_base.py

fused_moe_modular_method.py

hpc_moe.py

layer.py

modular_kernel.py

moe_align_block_size.py

moe_fused_mul_sum.py

moe_output.py

moe_permute_unpermute.py

routed_experts.py

routed_experts_capturer.py

topk_weight_and_reduce.py

unquantized_fused_moe_method.py

utils.py