[Doc] add load_format items in docs (#14804)

wwl2755 committed over 1 year ago

[FEAT] [ROCm]: Add AITER RMS Norm (Layer Norm) Feature (#14959)

TJian committed over 1 year ago

[Bugfix][V0] Multi-sequence logprobs streaming edge case (#15259)

Andy Lo committed over 1 year ago

[Misc] Increase RayDistributedExecutor RAY_CGRAPH_get_timeout (#15301)

Rui Qiao committed over 1 year ago

[Build/CI] Fix env var typo (#15305)

Russell Bryant committed over 1 year ago

[TPU][V1] MHA Pallas backend (#15288)

Nicolò Lucchesi committed over 1 year ago

Revert "[Feature] specify model in config.yaml (#14855)" (#15293)

Cyrus Leung committed over 1 year ago

[Bugfix][VLM] fix llava processor (#15285)

Mengqing Cao committed over 1 year ago

[v1] Refactor KVCacheConfig (#14079)

Chen Zhang committed over 1 year ago

[Misc] Add cProfile helpers (#15074)

Russell Bryant committed over 1 year ago

[Bugfix] Fix broken kernel test due to missing rename for v1 Triton backend (#15282)

Isotr0py committed over 1 year ago

[V1] Fix wrong import path of get_flash_attn_version (#15280)

Lehua Ding committed over 1 year ago

[Bugfix] Fix incorrect resolving order for transformers fallback (#15279)

Isotr0py committed over 1 year ago

[Misc] Add attention mask pre-computation optimization back to Qwen2.5-VL (#15273)

Isotr0py committed over 1 year ago

[Bugfix] Add int8 torch dtype for KVCache (#15260)

Shanshan Shen committed over 1 year ago

[Feature] specify model in config.yaml (#14855)

Wei Zeng committed over 1 year ago

[V1] Avoid redundant input processing in n>1 case (#14985)

Nick Hill committed over 1 year ago

[Doc] Update LWS docs (#15163)

Edwin Hernandez committed over 1 year ago

[V1] Enable Triton(ROCm) Attention backend for Nvidia GPUs (#14071)

Isotr0py committed over 1 year ago

[Hardware][TPU] Add check for no additional graph compilation during runtime (#14710)

Siyuan Liu committed over 1 year ago