[Misc] Fix circular import in vllm.transformers_utils.config (#30179)

Ye (Charlotte) Qi committed 11 months ago

Support tokenization_kwargs override (#29794)

Yu Jiaqi committed 11 months ago

[Chore] Deprecate `SupportsMultiModal.merge_by_field_config` (#30170)

Cyrus Leung committed 11 months ago

prefix caching design doc sha256 now default (#29261)

redwrasse committed 11 months ago

[bugfix] fix type[AttentionBackend] bug in kv_connector_base_v1 (#30051)

kx committed 11 months ago

[Model Runner V2] Support min-p sampling (#30171)

Woosuk Kwon committed 11 months ago

[Misc] Move `disable_nccl_for_dp_synchronization` init logic into `VllmConfig` (#30161)

Nick Hill committed 11 months ago

[CI/Build][AMD] Use ROCM_ATTN instead of FLASH_ATTN test for test_register_kv_caches for ROCm and update test for TRITON_ATTN (#29985)

rasmith committed 11 months ago

[Bugfix]: Fix `TokenizerLike` interface (#30009)

Rohan Potdar committed 11 months ago

[Model] Add support for transformer-based Ultravox v0.7 projector (#30089)

Peter Salas committed 11 months ago

fix#30092 Kimi-Linear model loading failure with missing indexer_rotary_emb (#30093)

Dongjie Zou committed 11 months ago

Fix AWQ MoE marlin check issue in marlin_utils.py for AMD backend (#30102)

yuttian1 committed 11 months ago

[CI/Build][AMD] Skip marlin, machete, and hadacore tests since these require _C functions not defined for ROCm (#30109)

rasmith committed 11 months ago

Better error when world size is larger than node and `distributed_executor_backend` is not set (#30140)

Harry Mellor committed 11 months ago

[CI]: Remove unnecessary imports from test_lmache_integration (#30157)

Samuel Shen committed 11 months ago

[CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils to use hip.libdevice.round (#30151)

rasmith committed 11 months ago

[Tests] Tool call tests for openai/gpt-oss-20b (#26237)

Deboleina committed 11 months ago

[Bug] Fix vLLM config is not set error (#29999)

Wentao Ye committed 11 months ago

let draft model follow target model's config_format (#30152)

Bangsheng Tang committed 11 months ago

[Bugfix][llama4_eagle] Fix missing 'lm_head' attribute (#29926)

Divakar Verma committed 11 months ago