[Bugfix] Fix LoRA test (#18123)

Jee Jee Li committed over 1 year ago

[FEAT] [ROCm]: Add AITER CK 2 Stages MoE support (#17110)

TJian committed over 1 year ago

[Bugfix] Fix QKVCrossParallelLinear::sync_weight_attrs for PyTorch compile (#17844)

Andrzej Kotłowski committed over 1 year ago

[Misc] replace does not exist model (#18119)

rongfu.leng committed over 1 year ago

[Model] Add packed_modules_mapping for Qwen3-MOE (#18118)

Jee Jee Li committed over 1 year ago

[Bugfix] Fix entrypoints audio test failure (#18111)

Cyrus Leung committed over 1 year ago

[New Model]: support GTE NewModel (#17986)

wang.yuqi committed over 1 year ago

[Bugfix][Example] make lmcache v0 work. (#18051)

majianpeng committed over 1 year ago

[Bugfix] fix moe marlin `topk_weight` loading (#18080)

Jinzhen Lin committed over 1 year ago

[Fix] Move "model_config" as keyword args in chat_utils.py (#18098)

lkchen committed over 1 year ago

Fix broken example: examples/offline_inference/profiling at scheduler_config (#18117)

Ecthlion_zyy committed over 1 year ago

[BugFix][AMD] Compatible patch for AITER lib after 04/20 (#17912)

qli88 committed over 1 year ago

[AMD][torch.compile] Enable silu+fp8_quant fusion for rocm (#18082)

Charlie Fu committed over 1 year ago

[FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 (#17955)

vllmellm committed over 1 year ago

[Bugfix][V1] Fix FlashInfer V1 backend using the wrong VllmConfig (#18086)

Michael Goin committed over 1 year ago

[Bugfix] Fix FP8 Marlin MoE and enable for compressed-tensors models (#18026)

Michael Goin committed over 1 year ago

[core][distributed] add ep group and all2all interface (#18077)

youkaichao committed over 1 year ago

[Bug]: Fix S3 model/tokenizer path resolution (#18083)

Jon Gill committed over 1 year ago

[Misc] Remove unused numpy tensor (#18084)

Roger Wang committed over 1 year ago

[P/D] Add some more debug logs to `NixlConnector` (#18102)

Nick Hill committed over 1 year ago