[V1][Easy] Add empty allowed_token_ids in the v1 sampler test (#14308)

Lu Fang committed over 1 year ago

[misc] Add FlashMLA as a new option of VLLM_ATTENTION_BACKEND env (#14267)

Serena committed over 1 year ago

[V1][BugFix] Fix for mixed top_k batch (#14301)

Nick Hill committed over 1 year ago

Deprecate `best_of` Sampling Parameter in anticipation for vLLM V1 (#13997)

Vincent committed over 1 year ago

[V1][Minor] Remove obsolete FIXME comment (#14304)

Nick Hill committed over 1 year ago

[Docs] Add Meta Slides (#14297)

Simon Mo committed over 1 year ago

[Bugfix] Fix broken vision language example (#14292)

Isotr0py committed over 1 year ago

prefix_caching.md: Fixed typo (#14293)

DaividFrank committed over 1 year ago

[Misc] Add Qwen2MoeForCausalLM moe tuning support (#14276)

Jee Jee Li committed over 1 year ago

[LoRA] Remove linear hack outside transformers backend (#14177)

Isotr0py committed over 1 year ago

[V1][Frontend] Add Testing For V1 Runtime Parameters (#14159)

Robert Shaw committed over 1 year ago

Small update for external_launcher backend docs (#14288)

Zhe Zhang committed over 1 year ago

[Doc] [3/N] Refer code examples for common cases in dev multimodal processor (#14278)

Cyrus Leung committed over 1 year ago

[Doc] Update nginx guide: remove privileged from vllm container run and add target GPU ID (#14217)

Iacopo Poli committed over 1 year ago

[Bugfix][V1] Fix allowed_token_ids for v1 Sampler (#14169)

Lu Fang committed over 1 year ago

[Misc][V1] Avoid using `envs.VLLM_USE_V1` in mm processing (#14256)

Roger Wang committed over 1 year ago

[Frontend] Allow return_tokens_as_token_ids to be passed as a request param (#14066)

Benjamin Chislett committed over 1 year ago

Temporarily disable test_awq_gemm_opcheck (#14251)

Michael Goin committed over 1 year ago

[platforms] improve rocm debugging info (#14257)

youkaichao committed over 1 year ago

[V1] EP/TP MoE + DP Attention (#13931)

Tyler Michael Smith committed over 1 year ago