Jee Jee Li 4635cc3e8f Shard the K3 Latent-MoE up-projection on large batches (#50383)

2026-08-03 00:49:39 -07:00

..

configs

[Model] Optimize Qwen3.5 on H20 (#48350)

2026-07-13 03:30:48 +00:00

experts

[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)

2026-08-03 14:55:04 +08:00

oracle

[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)

2026-08-03 14:55:04 +08:00

prepare_finalize

[New model] Kimi K3 (#50000)

2026-07-30 03:49:58 -07:00

router

perf: dispatch non-grouped bias-less topk routing methods to fused path (#49618)

2026-07-28 14:57:22 -07:00

runner

Shard the K3 Latent-MoE up-projection on large batches (#50383)

2026-08-03 00:49:39 -07:00

__init__.py

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

activation.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

all2all_utils.py

[Kernel] TD operand loads for batched MoE GEMM (moe_mmk) on XPU (#46340)

2026-07-26 08:50:07 +08:00

config.py

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

deep_gemm_utils.py

[Kimi K3 Bug] Fix deepgemm support for kimi k3 (#50458)

2026-07-30 20:10:16 -04:00

eep_reconfigure.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

expert_map_manager.py

[MoE Refactor] Move expert map related code into ExpertMapManager class (#41046)

2026-05-12 09:18:27 -04:00

fused_flydsl_moe.py

[ROCm] Pass pointers to FlyDSL MoE kernels (#50378)

2026-07-30 12:49:26 -07:00

fused_moe_method_base.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

fused_moe_modular_method.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

fused_moe.py

fused_moe: add VLLM_TRITON_USE_TD tensor-descriptor path (#42436)

2026-07-29 13:15:10 +08:00

hpc_moe.py

[MoE Backend] add HPC-Ops MoE backend (#45924)

2026-06-27 11:18:07 +08:00

layer.py

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

modular_kernel.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

moe_align_block_size.py

[Kernel][MoE] optimize moe_align_block_size (#29642)

2025-12-07 01:58:47 -08:00

moe_fused_mul_sum.py

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

moe_permute_unpermute.py

[Bug] Fix torch device issue for MOE permute (#44005)

2026-05-29 18:55:00 +00:00

routed_experts_capturer.py

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

routed_experts.py

[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)

2026-07-31 14:13:03 -07:00

topk_weight_and_reduce.py

[Kernel] TD operand loads for batched MoE GEMM (moe_mmk) on XPU (#46340)

2026-07-26 08:50:07 +08:00

unquantized_fused_moe_method.py

[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)

2026-08-03 14:55:04 +08:00

utils.py

fused_moe: add VLLM_TRITON_USE_TD tensor-descriptor path (#42436)

2026-07-29 13:15:10 +08:00