[Bugfix]Change the exception thrown by call_hf_processor from RuntimeError to ValueError (#18181)

Zhonghua Deng committed over 1 year ago

[Frontend] Fix chat template content format detection (#18190)

Sebastian Schoennenbeck committed over 1 year ago

Improve examples rendering in docs and GitHub (#18203)

Harry Mellor committed over 1 year ago

Adding "Basic Models Test" and "Multi-Modal Models Test (Extended) 3" in AMD Pipeline (#18106)

Alexei-V-Ivanov-AMD committed over 1 year ago

[Kernel] [V1] Fix performance regression for triton unified attention (#18161)

Thomas Parnell committed over 1 year ago

add tools into TokenizeChatRequest (#18187)

hustxiayang committed over 1 year ago

Update deprecated type hinting in `model_loader` (#18130)

Harry Mellor committed over 1 year ago

fix: typos (#18151)

omahs committed over 1 year ago

[V1] Update zmq socket creation in nixl connector (#18148)

Russell Bryant committed over 1 year ago

[CI] don't skip fixed `test_kv_cache_events()` (#18183)

David Xia committed over 1 year ago

[Bugfix] Fix FusedMoEPrepareAndFinalize for cuda-disalike backends (#18178)

Mengqing Cao committed over 1 year ago

[Model] Allow the use of sliding window in Qwen2 (#17772)

inkcherry committed over 1 year ago

[UT] Add ut for none hash (#17892)

Ning Xie committed over 1 year ago

Support custom implementations of VideoLoader backends. (#18091)

Chenheli Hua committed over 1 year ago

[Bugfix] Fix fp8 tests for triton_unified_attention for Triton 3.3 (#18013)

Thomas Parnell committed over 1 year ago

Update deprecated type hinting in `models` (#18132)

Harry Mellor committed over 1 year ago

[Fix][ROCm] Enforce eager for all encoder-decoder models on ROCm (#18154)

Luka Govedič committed over 1 year ago

[Misc] add lobe-chat support (#18177)

Reid committed over 1 year ago

[Chore] astral's ty (#18116)

Aaron Pham committed over 1 year ago

[V1][Metrics] Remove unused code (#18158)

Mark McLoughlin committed over 1 year ago