vLLM/vllm at 7379b3d4b2e0b85de43e7c5145ff26c8200aac8a - vLLM

adapter_commons

[CI/Build] Update Ruff version (#8469 )

2024-09-18 11:00:56 +00:00

assets

[CI/Build] Update CPU tests to include all "standard" tests (#5481 )

2024-11-08 23:30:04 +08:00

attention

[Misc] Allow passing logits_soft_cap for xformers backend (#11252 )

2024-12-17 00:37:04 -08:00

compilation

[torch.compile] fast inductor (#11108 )

2024-12-16 16:15:22 -08:00

core

[Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion (#7209 )

2024-12-14 11:38:10 -08:00

distributed

[Core] Support disaggregated prefill with Mooncake Transfer Engine (#10884 )

2024-12-15 21:28:18 +00:00

engine

[Feature] Add load generation config from model (#11164 )

2024-12-19 10:50:38 +00:00

entrypoints

[Feature] Add load generation config from model (#11164 )

2024-12-19 10:50:38 +00:00

executor

[Misc] Optimize ray worker initialization time (#11275 )

2024-12-18 23:38:02 -08:00

inputs

[VLM] Merged multimodal processor for Qwen2-Audio (#11303 )

2024-12-19 06:14:17 +00:00

logging_utils

Rename vllm.logging to vllm.logging_utils (#10134 )

2024-11-08 20:53:24 +00:00

lora

[Misc] Minor improvements to the readability of PunicaWrapperBase (#11200 )

2024-12-14 16:38:27 +00:00

model_executor

[V1] Fix multimodal profiling for Molmo (#11325 )

2024-12-19 16:27:22 +00:00

multimodal

[VLM] Merged multimodal processor for Qwen2-Audio (#11303 )

2024-12-19 06:14:17 +00:00

platforms

[Platform] platform agnostic for EngineArgs initialization (#11225 )

2024-12-16 22:11:06 -08:00

plugins

[Core] Cleanup startup logging a bit (#10961 )

2024-12-07 02:30:23 +00:00

profiler

[misc] Layerwise profile updates (#10242 )

2024-12-16 18:14:57 +00:00

prompt_adapter

[CI/Build] drop support for Python 3.8 EOL (#8464 )

2024-11-06 07:11:55 +00:00

spec_decode

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975 )

2024-12-07 17:20:49 +00:00

transformers_utils

[Bugfix] Fix guided decoding with tokenizer mode mistral (#11046 )

2024-12-17 22:34:08 -08:00

triton_utils

[LoRA][Kernel] Remove the unused libentry module (#10214 )

2024-11-11 09:43:23 +00:00

usage

mypy: check additional directories (#9162 )

2024-10-08 22:08:22 +00:00

v1

[V1] Fix multimodal profiling for Molmo (#11325 )

2024-12-19 16:27:22 +00:00

vllm_flash_attn

[ci][build] fix vllm-flash-attn (#8699 )

2024-09-21 23:24:58 -07:00

worker

[Model] Add JambaForSequenceClassification model (#10860 )

2024-12-19 22:48:06 +08:00

__init__.py

[Frontend] Separate pooling APIs in offline inference (#11129 )

2024-12-13 10:40:07 +00:00

_custom_ops.py

[Bugfix][Build/CI] Fix sparse CUTLASS compilation on CUDA [12.0, 12.2) (#11311 )

2024-12-19 02:43:30 +00:00

_ipex_ops.py

[Misc][XPU] Upgrade to Pytorch 2.5 for xpu backend (#9823 )

2024-11-06 17:29:03 -08:00

beam_search.py

[Frontend] re-enable multi-modality input in the new beam search implementation (#9427 )

2024-10-29 11:49:47 +00:00

block.py

[mypy] Enable mypy type checking for vllm/core (#7229 )

2024-08-28 07:11:14 +08:00

config.py

[Feature] Add load generation config from model (#11164 )

2024-12-19 10:50:38 +00:00

connections.py

[core][distributed] fix zmq hang (#6759 )

2024-07-24 17:37:12 -07:00

envs.py

[torch.compile] fast inductor (#11108 )

2024-12-16 16:15:22 -08:00

forward_context.py

[torch.compile] allow tracking forward time (#11081 )

2024-12-14 19:45:00 -08:00

logger.py

[Core] Fix broken log configuration (#10458 )

2024-11-23 10:23:51 +08:00

logits_process.py

[Frontend] Bad words sampling parameter (#9717 )

2024-10-26 16:29:38 +00:00

outputs.py

[Doc] Reorganize online pooling APIs (#11172 )

2024-12-14 00:22:22 +08:00

pooling_params.py

[Frontend] Chat-based Embeddings API (#9759 )

2024-11-01 08:13:35 +00:00

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509 )

2023-10-30 14:50:47 -07:00

sampling_params.py

[bugfix] fixed parameter “n” when set parameter “bestof” > 1 (#10854 )

2024-12-04 08:48:22 +00:00

scalar_type.py

[Bugfix] Fix support for dimension like integers and ScalarType (#9299 )

2024-10-17 19:08:34 +00:00

scripts.py

[Frontend] Add --version flag to CLI (#10369 )

2024-11-15 13:13:53 -08:00

sequence.py

[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (#8240 )

2024-12-13 07:51:25 -08:00

tracing.py

[misc] hide best_of from engine (#9261 )

2024-10-10 21:30:44 -07:00

utils.py

[VLM] Merged multimodal processor for Qwen2-Audio (#11303 )

2024-12-19 06:14:17 +00:00

version.py

[CI/Build] use setuptools-scm to set __version__ (#4738 )

2024-09-23 09:44:26 -07:00