[V1][Structured Output] Move xgrammar related utils to `backend_xgrammar.py` (#16578)

Shanshan Shen committed over 1 year ago

[ROCM] Bind triton version to 3.2 in requirements-built.txt (#16664)

Sage Moore committed over 1 year ago

[Feature] add model aware kv ops helper (#16020)

billishyahao committed over 1 year ago

Disable remote caching when calling compile_fx (#16611)

Richard Zou committed over 1 year ago

[Misc] Modify LRUCache touch (#16689)

Jee Jee Li committed over 1 year ago

[Bugfix] fix gpu docker image mis benchmarks dir (#16628)

rongfu.leng committed over 1 year ago

[Model] Add PLaMo2 (#14323)

Shinichi Hemmi committed over 1 year ago

[Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server (#10546)

Angky William committed over 1 year ago

[Misc] Update `compressed-tensors` WNA16 to support zero-points (#14211)

Dipika Sikka committed over 1 year ago

[Kernel] Remove redundant Exp calculations (#16123)

DefTruth committed over 1 year ago

Add "/server_info" endpoint in api_server to retrieve the vllm_config.  (#16572)

Xihui Cang committed over 1 year ago

[CI/Build] Fix LoRA OOM (#16624)

Jee Jee Li committed over 1 year ago

[Misc] refactor argument parsing in examples (#16635)

Reid committed over 1 year ago

Fix vLLM x torch.compile config caching (#16491)

Richard Zou committed over 1 year ago

Add `vllm bench [latency, throughput]` CLI commands (#16508)

Michael Goin committed over 1 year ago

[Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) (#16631)

Pooya Davoodi committed over 1 year ago

[Bugfix] Fix tests/kernels/test_mamba_ssm_ssd.py (#16623)

Tyler Michael Smith committed over 1 year ago

[BugFix]: Update minimum `pyzmq` version (#16549)

Taneem Ibrahim committed over 1 year ago

[Kernel] moe wna16 marlin kernel (#14447)

Jinzhen Lin committed over 1 year ago

[Core][Bugfix] Fix Offline MM Beam Search (#16390)

Alex Brooks committed over 1 year ago