3 people 044b05220e [Kernel][Perf] Tune fused_moe FP8 config for Qwen3.5 on L40S (+7%) (#53819) ...

Signed-off-by: nizhang1 <nizhang1@coupang.com>
Co-authored-by: nizhang1 <nizhang1@coupang.com>
Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

2026-08-26 04:02:26 +00:00

..

determinism

[Perf] Autotune batch invariance triton kernel in blackwell, 33.6% E2E latency reduction (#53649)

2026-08-25 15:06:01 -04:00

hw_agnostic

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00

kernels

[Kernel] Add FlashInfer TRTLLM MXFP8 linear backend (#52204)

2026-08-20 10:07:22 -04:00

layers

[Kernel][Perf] Tune fused_moe FP8 config for Qwen3.5 on L40S (+7%) (#53819)

2026-08-26 04:02:26 +00:00

model_loader

Add routed expert loading for gpt-oss (#52209)

2026-08-23 17:59:08 +08:00

models

[Bugfix][LoRA] Enable tower/connector LoRA for Qwen3-Omni (#53557)

2026-08-26 10:44:41 +08:00

offloader

Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)

2026-07-06 14:18:33 +01:00

warmup

[Core] drop duplicate VLLM_USE_DEEP_GEMM check (#48687)

2026-08-24 16:30:50 +00:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

[Bugfix] Reject contradictory custom-op directives (#49134)

2026-07-26 08:42:14 -04:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

[Weight processing] Copy over new_data attributes in replace_parameter (#49601)

2026-08-06 13:03:37 -04:00