[CPU] Refine default config for the CPU backend (#19539)

Li, Jiang committed over 1 year ago

[Misc] Correct broken docs link (#19553)

Hyogeun Oh (오효근) committed over 1 year ago

[doc] fix incorrect link (#19586)

Reid committed over 1 year ago

[Doc] uses absolute links for structured outputs (#19582)

Aaron Pham committed over 1 year ago

[Bugfix] Fix EAGLE vocab embedding for multimodal target model (#19570)

qizixi committed over 1 year ago

[BugFix] : Fix Batched DeepGemm Experts (#19515)

Varun Sundar Rabindranath committed over 1 year ago

Revert "[Build/CI] Add tracing deps to vllm container image (#15224)" (#19378)

kourosh hakhamaneshi committed over 1 year ago

[V1] Resolve failed concurrent structured output requests (#19565)

Russell Bryant committed over 1 year ago

[Doc] Unify structured outputs examples (#18196)

Aaron Pham committed over 1 year ago

[Bugfix] Enforce contiguous input for dynamic_per_token FP8/INT8 quant (#19452)

Michael Goin committed over 1 year ago

[Misc] Turn MOE_DP_CHUNK_SIZE into an env var (#19506)

Varun Sundar Rabindranath committed over 1 year ago

[Spec Decode][Benchmark] Generalize spec decode offline benchmark to more methods and datasets (#18847)

Ekagra Ranjan committed over 1 year ago

[doc] Make top navigation sticky (#19540)

Reid committed over 1 year ago

[torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756)

Luka Govedič committed over 1 year ago

Fix TorchAOConfig skip layers (#19265)

mobicham committed over 1 year ago

[Perf] Vectorize static / dynamic INT8 quant kernels (#19233)

Wentao Ye committed over 1 year ago

[V1][NixlConnector] Drop `num_blocks` check (#19532)

Nicolò Lucchesi committed over 1 year ago

[Doc] Add V1 column to supported models list (#19523)

Cyrus Leung committed over 1 year ago

[Quantization] Improve AWQ logic (#19431)

Jee Jee Li committed over 1 year ago

[Bugfix] Respect num-gpu-blocks-override in v1 (#19503)

jmswen committed over 1 year ago