vLLM/vllm at 2b22290ce01b033cc692e7dce159d74a43f6f2c5 - vLLM

adapter_commons

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

assets

[Misc] Upgrade to Python 3.9 typing for additional directories (#14492 )

2025-03-08 17:35:50 +00:00

attention

[Attention] Flash Attention 3 - fp8 (#14570 )

2025-03-20 01:14:20 -04:00

benchmarks

[Feature] Add vllm bench CLI (#13993 )

2025-03-12 00:31:48 +00:00

compilation

Correct capitalisation: VLLM -> vLLM (#14562 )

2025-03-10 16:36:21 +00:00

core

[FEAT]Support reset prefix cache by specified device (#15003 )

2025-03-19 10:54:41 -07:00

device_allocator

[sleep mode] error out with expandable_segments (#14189 )

2025-03-04 18:54:19 +08:00

distributed

[Frontend][Bugfix] support prefill decode disaggregation on deepseek (#14824 )

2025-03-20 00:00:33 -07:00

engine

[V1] Add flag to disable cascade attention (#15243 )

2025-03-20 15:24:16 -07:00

entrypoints

[Misc]fixed disable these http request logs (#14754 )

2025-03-19 21:53:40 -07:00

executor

Fix env vars for running Ray distributed backend on GKE (#15166 )

2025-03-20 14:59:33 +00:00

inputs

[V1] Remove input cache client (#14864 )

2025-03-16 23:42:06 -07:00

logging_utils

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

lora

[Misc] Embedding model support LoRA (#14935 )

2025-03-18 12:07:00 +00:00

model_executor

[Bugfix] Multi-video inference on LLaVA-Onevision (#15082 )

2025-03-20 14:10:45 +00:00

multimodal

[Bugfix] Fix embedding assignment for InternVL-based models (#15086 )

2025-03-20 03:40:13 +00:00

platforms

Fix env vars for running Ray distributed backend on GKE (#15166 )

2025-03-20 14:59:33 +00:00

plugins

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

profiler

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

prompt_adapter

[Misc] set single whitespace between log sentences (#13771 )

2025-02-25 10:26:12 +08:00

spec_decode

[Bugfix] EAGLE output norm bug (#14464 )

2025-03-15 06:50:33 +00:00

third_party

[core] port pynvml into vllm codebase (#12963 )

2025-02-09 15:00:00 +08:00

transformers_utils

Fixing Imprecise Type Annotations (#15192 )

2025-03-20 01:19:55 -07:00

triton_utils

[Frontend] Remove custom_cache_manager (#13791 )

2025-03-20 00:13:50 +08:00

usage

[Misc] Upgrade to Python 3.9 typing for additional directories (#14492 )

2025-03-08 17:35:50 +00:00

v1

[V1] Add flag to disable cascade attention (#15243 )

2025-03-20 15:24:16 -07:00

vllm_flash_attn

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

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

worker

Revert "[Bugfix] Limit profiling run sequence length by max_model_len (#14785 ) (#14892 )

2025-03-16 09:13:46 -07:00

__init__.py

[MISC] Always import version library first in the vllm package (#12979 )

2025-02-09 18:56:40 +08:00

_custom_ops.py

[ROCm][Bugfix] Ensure that the moe_wna16_gemm kernel is not built on ROCm platforms. (#14629 )

2025-03-12 08:00:28 -04:00

_ipex_ops.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

beam_search.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

config.py

[V1] Add flag to disable cascade attention (#15243 )

2025-03-20 15:24:16 -07:00

connections.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

envs.py

[Attention] Flash Attention 3 - fp8 (#14570 )

2025-03-20 01:14:20 -04:00

fa_utils.py

[Attention] Flash Attention 3 - fp8 (#14570 )

2025-03-20 01:14:20 -04:00

forward_context.py

[Bugfix] Remove num_tokens_across_dp (#14302 )

2025-03-05 23:55:55 +00:00

jsontree.py

[VLM] Limit multimodal input cache by memory (#14805 )

2025-03-15 02:52:05 -07:00

logger.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

logits_process.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

outputs.py

[BugFix][V1] Fix parallel sampling finishing/aborts (#14512 )

2025-03-12 10:29:48 -07:00

pooling_params.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

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][V1] Fix overhead related to bad_words sampling when not in use (#14894 )

2025-03-16 14:53:34 -07:00

scalar_type.py

[NVIDIA] Support nvfp4 quantization (#12784 )

2025-02-12 19:51:51 -08:00

scripts.py

[Frontend] Move CLI code into vllm.cmd package (#12971 )

2025-02-12 23:12:21 -08:00

sequence.py

[Bugfix] EAGLE output norm bug (#14464 )

2025-03-15 06:50:33 +00:00

test_utils.py

Use smaller embedding model when not testing model specifically (#13891 )

2025-02-28 00:50:43 -08:00

tracing.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

utils.py

[FrontEnd][Perf] merge_async_iterators fast-path for single-prompt requests (#15150 )

2025-03-19 21:04:41 +00:00

version.py

[Metrics] Add --show-hidden-metrics-for-version CLI arg (#13295 )

2025-02-22 00:20:45 -08:00