[ROCm] Fallback pytorch GELU with tanh approximation to GELU() (#29244)

Divakar Verma committed 12 months ago

SM120 / NVFP4: add device guard and runtime SM dispatch to cutlass_scaled_fp4_mm (#29711)

Hendrik Holtmann committed 12 months ago

[BugFix] Preserve spec decoding uniform decode when scheduling (#29759)

Nick Hill committed 12 months ago

Updated CI mirror 2025-11-25 (#29434)

Alexei-V-Ivanov-AMD committed 12 months ago

Revert #29787 and #29690 (#29815)

Kevin H. Luu committed 12 months ago

[Ascend]: Fixed the issue where OOT Platform vllm-ascend could not enable SP in Eager mode (#28935)

Nengjun Ma committed 12 months ago

Update FAQ on interleaving sliding windows support (#29796)

Finbarr Timbers committed 12 months ago

[Core][Observability] Add KV cache residency metrics (#27793)

shivampr committed 12 months ago

[ci] Make distributed 8 gpus test optional (#29801)

Kevin H. Luu committed 12 months ago

[Bugfix] Missing cached item in the MultiModalReceiverCache (#28525)

knlnguyen1802 committed 12 months ago

[Hardware][AMD] Remove ROCm skip conditions for transformers backend tests (#29782)

BADAOUI Abdennacer committed 12 months ago

[Frontend] add 'verbose_json' and 'timestamp' feature on Whisper Transcription/Translation (#24209)

sangbumlikeagod committed 12 months ago

[Doc] Update description disable_any_whitespace (#29784)

FredericOdermatt committed 12 months ago

[CI] fix url-encoding behavior in nightly metadata generation (#29787)

Shengqi Chen committed 12 months ago

[Doc] fix heading levels (#29783)

Liu Jinyi committed 12 months ago

[CI] Renovation of nightly wheel build & generation (#29690)

Shengqi Chen committed 12 months ago

[Bugfix] TypeError: 'NoneType' object is not callable (#29414)

Marcin Ostrowski committed 12 months ago

[v1] Add real sliding window calculation to FlexAttention direct BlockMask building (#26015)

Isotr0py committed 12 months ago

[multimodal][test] Reduce memory utilization for test_siglip to avoid OOM (#29504)

Zhengxu Chen committed 12 months ago

[XPU] Fix AWQ skipped layer detection in IPEX quantization (#29774)

Fanli Lin committed 12 months ago