[Doc]: fix typos in Python comments (#24026)

Didier Durand committed about 1 year ago

[Kernel] Update DeepGEMM to latest commit (#23915)

Jee Jee Li committed about 1 year ago

[Frontend] Update the warning log when using VLLM_ALLOW_LONG_MAX_MODEL_LEN (#20904)

wang.yuqi committed about 1 year ago

[Misc] Enable V1 FP16 inference on pre-Ampere GPUs (#24022)

Isotr0py committed about 1 year ago

[Misc] add hash_function doc string (#24014)

Ning Xie committed about 1 year ago

[Bugfix] Add support for `<tool_call>` format in streaming mode for XLAM Tool Parser (#22769)

Code Jesus committed about 1 year ago

[Misc] IO Processor plugins for pooling models (#22820)

Christian Pinto committed about 1 year ago

Migrate Phi4 inputs to TensorSchema (#23471)

Benji Beck committed about 1 year ago

[Misc] refactor code by import as for torch._inductor.config (#23677)

Ning Xie committed about 1 year ago

[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357)

Isotr0py committed about 1 year ago

[Misc] Move fast prefill logic to separate method (#24013)

Woosuk Kwon committed about 1 year ago

Fix the bug related to loading GPTP INT3 weights. (#23328)

Jun-Howie committed about 1 year ago

[Misc] Avoid redundant copy for encoder-only models (#24012)

Woosuk Kwon committed about 1 year ago

[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994)

JartX committed about 1 year ago

v1: Support KV events from connectors (#19737)

Or Ozeri committed about 1 year ago

[Minor] Fix some random typos in comments (#24009)

Nick Hill committed about 1 year ago

vllm fix check on max vocab size (#22471)

Xiaodong Wang committed about 1 year ago

[Doc]: fix typos in Python comments (#24001)

Didier Durand committed about 1 year ago

[Core][Multimodal] Allow passing `multi_modal_uuids` as multimodal identifiers. (#23394)

Roger Wang committed about 1 year ago

Fix wrong truncate_prompt_tokens type hint (#22761)

Gabriel Marinho committed about 1 year ago