[BugFix] register quant scale tensors as buffer (#31395)

Boyuan Feng committed 11 months ago

add tip for VLLM_USE_PRECOMPILED arg to reduce docker build time (#31385)

yitingdc committed 11 months ago

[MoE Refactor][10/N] Cleanup Fp8 Process Weights After Loading (#31169)

Robert Shaw committed 11 months ago

[BugFix] Fix cache issue in compilation_config (#31376)

Boyuan Feng committed 11 months ago

[Chore]: Remove HF format Phi4-MM examples (#31405)

Isotr0py committed 11 months ago

[CI/Build] Ignore max transformers version for more common tests (#31401)

Isotr0py committed 11 months ago

Fix/get raw stream patch #30905 (#30912)

baonudesifeizhai committed 11 months ago

[Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166)

Yifan Qiao committed 11 months ago

[XPU][CI]skip test_preprocess_error_handling due to fork/spawn issue (#31381)

Kunshang Ji committed 11 months ago

CustomOp: Unify aiter impl into GroupedTopk (#31221)

Xinyu Chen committed 11 months ago

[Docs] Add profiler user docs for http request (#31370)

rongfu.leng committed 11 months ago

[Mistral common] Ensure all functions are imported from the top & only use public methods (#31138)

Patrick von Platen committed 11 months ago

[Core] Initialize LoRA support for tower and connector in multi-modal models (#26674)

Jee Jee Li committed 11 months ago

[Docs] Fix some snippets (#31378)

Harry Mellor committed 11 months ago

[Misc] Fix Qwen2-MoE shared_expert_gate (#31339)

Jee Jee Li committed 11 months ago

[CI] Fix flaky vision beam search test with flexible semantic validation (#31324)

Andreas Karatzas committed 11 months ago

Support LoRA and GPTQModel for PLaMo 2/3 (#31322)

Shinichi Hemmi committed 11 months ago

[benchmark] use model card root instead of id (#31329)

Ning Xie committed 11 months ago

[CI/Build] Ignore max transformers version skipping for initialization tests (#30619)

Isotr0py committed 11 months ago

Feature/isaac 0.1 (#28367)

oscardev256 committed 11 months ago