Simplify `TokenizerGroup` (#16790)

Harry Mellor committed over 1 year ago

Disable enforce_eager for V1 TPU sampler and structured output tests (#17016)

Michael Goin committed over 1 year ago

[Chore] Remove Sampler from Model Code (#17084)

Woosuk Kwon committed over 1 year ago

Add docs for runai_streamer_sharded (#17093)

omer-dayan committed over 1 year ago

[doc] update to hyperlink (#17096)

Reid committed over 1 year ago

[V1] Update structured output (#16812)

Reid committed over 1 year ago

[Bugfix][Core] add seq_id_to_seq_group clearing to avoid memory leak when s… (#16472)

张宇 committed over 1 year ago

Addendum Fix to support FIPS enabled machines with MD5 hashing (#17043)

Areeb Syed committed over 1 year ago

More informative error when using Transformers backend (#16988)

Harry Mellor committed over 1 year ago

[Bugfix] Enable V1 usage stats (#16986)

Michael Goin committed over 1 year ago

[Minor] Use larger batch sizes for A100/B100/B200/MI300x (#17073)

Woosuk Kwon committed over 1 year ago

[Quantization]add prefix for commandA quantized model (#17017)

Chen Xia committed over 1 year ago

[CI/Build] workaround for CI build failure (#17070)

Sangyeon Cho committed over 1 year ago

[V1][Spec Decode] Always use argmax for sampling draft tokens (#16899)

Woosuk Kwon committed over 1 year ago

[BugFix][V1] Fix int32 token index overflow when preparing input ids (#16806)

Yong Hoon Shin committed over 1 year ago

[Frontend] Support guidance:no-additional-properties for compatibility with xgrammar (#15949)

Travis Johnson committed over 1 year ago

Use `@property` and private field for `data_parallel_rank_local` (#17053)

Harry Mellor committed over 1 year ago

`CacheConfig.block_size` should always be `int` when used (#17052)

Harry Mellor committed over 1 year ago

Improve Transformers backend model loading QoL (#17039)

Harry Mellor committed over 1 year ago

[CI] Update structured-output label automation (#17055)

Russell Bryant committed over 1 year ago