[Misc] Update transformers version limits of multi-modal tests (#16381)

Cyrus Leung committed over 1 year ago

[Model] use AutoWeightsLoader for deepseek_v2, internlm2 (#16383)

Aaron Ang committed over 1 year ago

fix sonnet dataset sample when prefix len is very small (#16379)

Chenyaaang committed over 1 year ago

[Bugfix][TPU] Fix TPU validate_request (#16369)

Michael Goin committed over 1 year ago

[misc] use tqdm.auto where appropriate (#16290)

Benjamin Kitor committed over 1 year ago

[CI][Bugfix] Pin triton version for CPU (#16384)

Roger Wang committed over 1 year ago

[bugfix] Avoid the time consumption caused by creating dummy videos. (#16371)

Jintao committed over 1 year ago

[TPU] Fix dummy loading OOM (#16372)

Chengji Yao committed over 1 year ago

[Model] use AutoWeightsLoader for granite, granitemoe, granitemoeshared, grok1, mixtral (#16325)

Aaron Ang committed over 1 year ago

[Bugfix]: do not shutdown server if `skip_special_use=False` for MistralTokenizer (#14094)

Guillaume Calmettes committed over 1 year ago

Add GLM-4-0414 support (#16338)

Yuxuan Zhang committed over 1 year ago

[TPU][V1] Refine tpu_model_runner to mitigate future recompilation issues (#16275)

Chengji Yao committed over 1 year ago

[Misc] refactor Structured Outputs example (#16322)

Reid committed over 1 year ago

[Hardware] add platform-specific request validation api (#16291)

Joe Runde committed over 1 year ago

[Build/CI] Add tracing deps to vllm container image (#15224)

Russell Bryant committed over 1 year ago

Fix `benchmark_throughput.py --backend=hf` (#16352)

Michael Goin committed over 1 year ago

[CI]Fix hpu docker and numpy version for CI (#16355)

Chendi.Xue committed over 1 year ago

[Bugfix] catch AssertionError in MistralTokenizer as ValueError (#16344)

Guillaume Calmettes committed over 1 year ago

[Bugfix] Fix profiling.py (#16202)

zh Wang committed over 1 year ago

Revert "Update label-tpu mergify and remove removal bot" (#16350)

Michael Goin committed over 1 year ago