[Doc] Update pooling model docs (#22186)

Cyrus Leung committed over 1 year ago

[Sampler] Support returning all logprobs or logits (#21792)

22quinn committed over 1 year ago

[Bugfix] Fix failing GGUF models test (#22174)

Isotr0py committed over 1 year ago

[feat] move WEIGHT_SCALE_SUPPORTED into raise block to accelerate RLHF weight loading (#21164)

Weixiao Huang committed over 1 year ago

[Misc] Modify the organization of GLM series (#22171)

Jee Jee Li committed over 1 year ago

[CI Bugfix] Fix wNa16 kernel not found for test_shared_storage_connector_hashes (#22163)

Tyler Michael Smith committed over 1 year ago

Remove index_put from MM embeddings merging (#22105)

Chenxi Yang committed over 1 year ago

[refactor] improve ConstantList exception specificity (#22156)

ZiTian.Zhao committed over 1 year ago

Add tree attention backend for v1 (part 1) (#20401)

Giancarlo Delfin committed over 1 year ago

remove duplicate code within cleanup_dist_env_and_memory (#22147)

Ning Xie committed over 1 year ago

[PD] add test for chat completions endpoint (#21925)

Abirdcfly committed over 1 year ago

[RLHF] Fix torch.dtype not serializable in example (#22158)

22quinn committed over 1 year ago

[fix] fix correct assertion syntax error in attention utils. (#22154)

ZiTian.Zhao committed over 1 year ago

Use `aiohttp` connection pool for benchmarking (#21981)

Seiji Eicher committed over 1 year ago

[Bugfix] Fix failing multimodal standard test (#22153)

Isotr0py committed over 1 year ago

fuse fp32 for GLM-4.5 e_score_correction_bias (#22143)

Yuxuan Zhang committed over 1 year ago

Add chat doc in quick start (#21213)

TankNee committed over 1 year ago

[CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to torch native implementation (#22145)

Li, Jiang committed over 1 year ago

[Responses API] Disable response store by default (#22137)

Woosuk Kwon committed over 1 year ago

[V1] [P/D] Refactor KV Connector Path (#21980)

David Ben-David committed over 1 year ago