fix: align lfm2 thumbnail token counting with HF (#36707)

tianshu-Michael-yu committed 8 months ago

Add 320 dimension size support to MLA (#36161)

Julien Denize committed 8 months ago

Fix `ExaoneMoeMTP` test that never ran in Transformers v4 (#36792)

Harry Mellor committed 8 months ago

[Misc] Clean up renderers (#36770)

Cyrus Leung committed 8 months ago

[Bugfix] Fix negative max_tokens when input prompt is too long (#36789)

Isotr0py committed 8 months ago

[CI] Add bfcl tool call correctness eval (#36560)

Flora Feng committed 8 months ago

[Bugfix] Fix DP/EP Shared Expert With Monolithic Kernels (#36061)

Robert Shaw committed 8 months ago

[torch.compile] Use FakeTensors instead of real GPU tensors for single-size compilation (#36093)

Richard Zou committed 8 months ago

Fix routed experts capture for hybrid models (Mamba + Attention) (#35744)

Hongxin Xu committed 8 months ago

Add 'none' reasoning effort to ChatCompletionRequest (#36238)

Julien Denize committed 8 months ago

Correct link to supported hardware on vllm.ai (#36798)

Harry Mellor committed 8 months ago

Add support to Mistral large 3 eagle with dense layers (#36163)

Julien Denize committed 8 months ago

Kimi k2.5 MLA based eagle3 (#36361)

Jhao-Ting Chen committed 8 months ago

Fix tied weights in weight mapping test for Transformers v5 (#36788)

Harry Mellor committed 8 months ago

[Model Runner V2] Remove unused warmup_for_prefill method (#36762)

Woosuk Kwon committed 8 months ago

[ROCm][Perf] Allow MTP lens > 1 in Sparse MLA (#36681)

tvirolai-amd committed 8 months ago

Disable docs build skipping until a better solution is found (#36790)

Harry Mellor committed 8 months ago

[Misc] Use envs module to get VLLM_DISABLED_KERNELS (#35776)

Martin Hickey committed 8 months ago

[Bugfix] Fix Mistral-small `--format` (#36782)

Silvia Colabrese committed 8 months ago

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230)

Wuxun Zhang committed 8 months ago