Disable outlines cache by default (#14837)

Russell Bryant committed over 1 year ago

Revert "[Model] Mamba2 Prefill Performance Tweaks: Fixing Flurry of U… (#14848)

Tyler Michael Smith committed over 1 year ago

[Bugfix][V1] Fix flashinfer sampling (#14815)

DefTruth committed over 1 year ago

[Neuron][CI] update docker run command (#14829)

Liangfu Chen committed over 1 year ago

[Bugfix] Fix torch_xla in V0 which can't handle None seed introduced … (#14844)

yarongmu-google committed over 1 year ago

[Doc] More neutral K8s deployment guide (#14084)

Yuan Tang committed over 1 year ago

[Build/CI] Upgrade aiohttp to incldue CVE fix (#14840)

Russell Bryant committed over 1 year ago

[Build/CI] Move ninja to common deps (#14835)

Russell Bryant committed over 1 year ago

[CI] Add TPU v1 test (#14834)

Richard Liu committed over 1 year ago

Update to torch==2.6.0 (#12721)

Michael Goin committed over 1 year ago

[V1] Fix model parameterization for structured output tests (#14833)

Russell Bryant committed over 1 year ago

[Model] Mamba2 Prefill Performance Tweaks: Fixing Flurry of Unnecessary Memory Copies (#14778)

Chih-Chieh Yang committed over 1 year ago

Re-enable the AMD Entrypoints Test (#14711)

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

[release] Remove log cleanup commands from TPU job (#14838)

Kevin H. Luu committed over 1 year ago

[Bugfix][Kernel]: Fix AllSpark kernel compilation errors and enable for CUDA < 12.0 (#14430)

Yajie Wang committed over 1 year ago

[Frontend] track server_load (#13950)

daniel-salib committed over 1 year ago

[V1][Metrics] Updated list of deprecated metrics in v0.8 (#14695)

Mark McLoughlin committed over 1 year ago

[Frontend] Fix log message to use http vs https (#14774)

Russell Bryant committed over 1 year ago

[V1] Fix vocab size calculation for structured output (#14826)

Russell Bryant committed over 1 year ago

[Bugfix] Fix Aria test loading (#14823)

Cyrus Leung committed over 1 year ago