[TPU]Fix KV cache sharing tests (#19371)

Siyuan Liu committed over 1 year ago

[Frontend] Make TIMEOUT_KEEP_ALIVE configurable through env var (#18472)

liusiqian-tal committed over 1 year ago

[Quantization] Bump compressed-tensors version (#19295)

Kyle Sayers committed over 1 year ago

[Bugfix][Core] Prevent token lengths exceeding `max_model_len` in V0 (#19348)

22quinn committed over 1 year ago

[Misc] Fixes and Optimizations for DeepEP + DeepGEMM combination. (#19298)

Varun Sundar Rabindranath committed over 1 year ago

[v1] Add fp32 support to v1 engine through flex attn (#19319)

Isotr0py committed over 1 year ago

[full_graph] Fix query_start_loc padding (#19321)

Yinghai Lu committed over 1 year ago

[Docs] Fix a bullet list in usage/security.md (#19358)

Michael Yao committed over 1 year ago

[CI] Introduce rules for llama auto-label (#19323)

Lu Fang committed over 1 year ago

[Fix] Allow kernel compilation for CUDA capability 8.7 (#19328)

Conroy Cheers committed over 1 year ago

[CI/Build] Fix LoRA test (#19350)

Jee Jee Li committed over 1 year ago

[Doc] Fix description in the Automatic Prefix Caching design doc (#19333)

Se7en committed over 1 year ago

[doc] improve ci doc (#19307)

Reid committed over 1 year ago

[Misc] Cleanup compilation tests (#19343)

Richard Zou committed over 1 year ago

[Frontend] Remove unreachable code from llm.py (#19288)

Kseniya Parkhamchuk committed over 1 year ago

[Misc] Add documentation update reminder to PR template (#19289)

Isotr0py committed over 1 year ago

[Deprecation] Remove `inputs` arg fallback in Engine classes (#18799)

Cyrus Leung committed over 1 year ago

[Bugfix] model_max_length should consider max_model_len in tokenizer_config (#19201)

wang.yuqi committed over 1 year ago

[Multi Modal] Add an env var for message queue max chunk bytes (#19242)

jennyyyyzhen committed over 1 year ago

[Quantization] Add compressed-tensors NVFP4 support (#18312)

Dipika Sikka committed over 1 year ago