chenjian 0d7f29841d [Cherry-pick] Fix bug in develop for eb5 (#4845) ...

* fix bug for PD EP

* fix

* optimize perf for engine worker queue

* fix bug

* fix internode ll two stage

* fix for ci

2025-11-06 14:01:42 +08:00

..

__init__.py

support w4afp8 EP inference (#3044)

2025-08-25 11:27:45 +08:00

ep.py

supports internode_ll_two_stage (#4162)

2025-11-04 16:35:40 +08:00

fused_moe_backend_base.py

[Cherry-pick] Fix bug in develop for eb5 (#4845)

2025-11-06 14:01:42 +08:00

fused_moe_cutlass_backend.py

【New Feature】W4afp8 supports per group quantization (#4272)

2025-11-05 21:00:23 +08:00

fused_moe_deepgemm_backend.py

[PD Disaggregation] Support Qwen3-MoE use PD + EP inference. (#4691)

2025-11-06 10:32:15 +08:00

fused_moe_marlin_backend.py

[noauxtc_kernel] remove useless code (#4643)

2025-10-30 18:59:04 +08:00

fused_moe_triton_backend.py

[BugFix]Dev fix custom ar unstable result (#4437)

2025-10-17 11:47:16 +08:00

fused_moe_wint2_backend.py

【New Feature】W4afp8 supports per group quantization (#4272)

2025-11-05 21:00:23 +08:00

moe.py

[PD Disaggregation] Support Qwen3-MoE use PD + EP inference. (#4691)

2025-11-06 10:32:15 +08:00

triton_moe_kernels.py

[OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00