vLLM/vllm at 0f71e24034263363e48cdc6ae036e7ca057a4f44 - vLLM

adapter_commons

Update deprecated type hinting in vllm/adapter_commons (#18073 )

2025-05-13 08:32:51 -07:00

assets

[Misc] Rename assets for testing (#17575 )

2025-05-02 03:29:25 -07:00

attention

[ROCm] Remove unnecessary assertion of max_model_len in ROCM_AITER_MLA attention backend. (#18938 )

2025-05-29 22:33:17 -07:00

benchmarks

[V1] fix torch profiling for V1 offline scenarios (#18445 )

2025-05-28 04:16:30 +00:00

compilation

Improve "failed to get the hash of the compiled graph" error (#18956 )

2025-05-30 15:00:54 +00:00

core

[Core] [Bugfix] Add Input Embeddings (#15428 )

2025-05-02 01:06:39 -07:00

device_allocator

Update deprecated type hinting in vllm/device_allocator and vllm/distributed (#18126 )

2025-05-14 04:07:57 -07:00

distributed

[P/D] NixlConnector DP fixes (#18903 )

2025-05-29 18:08:40 +00:00

engine

[Bugfix] Fix PP default fallback behavior for V1 (#18915 )

2025-05-30 10:13:17 +08:00

entrypoints

Tool parser regex timeout handling (#18960 )

2025-05-30 21:02:54 +00:00

executor

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663 )

2025-05-27 01:44:20 -07:00

inputs

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663 )

2025-05-27 01:44:20 -07:00

logging_utils

[CI] fix dump_input for str type (#18697 )

2025-05-26 18:23:35 +08:00

lora

[Perf] API-server scaleout with many-to-many server-engine comms (#17546 )

2025-05-30 08:17:00 -07:00

model_executor

[Misc] add group_size is -1 in awq quantization (#18910 )

2025-05-30 17:34:22 +00:00

multimodal

[Deprecation] Require overriding get_dummy_text and get_dummy_mm_data (#18796 )

2025-05-28 15:08:35 +08:00

platforms

[ROCm][V0][Attention] Revert to the previous FA triton kernel (#18226 )

2025-05-29 12:13:18 -04:00

plugins

[Misc] Reduce logs on startup (#18649 )

2025-05-24 23:03:53 -07:00

profiler

Update deprecated type hinting in vllm/profiler (#18057 )

2025-05-13 04:34:34 -07:00

prompt_adapter

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

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

reasoning

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

spec_decode

[Core] Automatically cast multi-modal input dtype (#18756 )

2025-05-27 23:45:48 +08:00

third_party

[BugFix] fix some typos found by typos. (#16314 )

2025-04-09 03:43:59 -07:00

transformers_utils

Prevent the cross-encoder logic from being applied to classification tasks (#18838 )

2025-05-28 19:16:17 -07:00

triton_utils

[Bugfix] Fix triton import with local TritonPlaceholder (#17446 )

2025-05-06 17:53:09 +08:00

usage

[MISC] fix typo (#18305 )

2025-05-17 10:52:09 -07:00

v1

[Perf] API-server scaleout with many-to-many server-engine comms (#17546 )

2025-05-30 08:17:00 -07:00

vllm_flash_attn

[BugFix] Fix vllm_flash_attn install issues (#17267 )

2025-04-27 17:27:56 -07:00

worker

[Neuron] Add multi-LoRA support for Neuron. (#18284 )

2025-05-29 16:41:22 +08:00

__init__.py

[misc] instruct pytorch to use nvml-based cuda check (#15951 )

2025-04-03 01:02:58 +08:00

_custom_ops.py

[ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control blockscale tensor allocation (#18160 )

2025-05-23 15:52:20 -07:00

_ipex_ops.py

[BugFix] Fix mla cpu - missing 3 required positional arguments (#17494 )

2025-05-01 14:36:52 +08:00

beam_search.py

[Core] Add Lora Support to Beam Search (#18346 )

2025-05-28 08:58:24 -07:00

collect_env.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

config.py

Skip device and quant Pydantic validation to make plugin device work (#18843 )

2025-05-28 20:12:30 -07:00

connections.py

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663 )

2025-05-27 01:44:20 -07:00

env_override.py

[misc] tune some env vars for GB200 (#16992 )

2025-04-23 10:59:48 +08:00

envs.py

Tool parser regex timeout handling (#18960 )

2025-05-30 21:02:54 +00:00

forward_context.py

[BugFix] Make DP work with connector-delayed new requests (#18559 )

2025-05-29 18:04:18 +00:00

jsontree.py

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

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

logger.py

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663 )

2025-05-27 01:44:20 -07:00

logits_process.py

[Bugfix] Fix bad words for Mistral models (#17753 )

2025-05-07 23:32:10 -07:00

outputs.py

[Deprecation] Remove fallbacks for Embeddings API (#18795 )

2025-05-28 15:09:04 +08:00

pooling_params.py

[Frontend] Using matryoshka_dimensions control the allowed output dimensions. (#16970 )

2025-04-24 07:06:28 -07:00

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

Change top_k to be disabled with 0 (still accept -1 for now) (#17773 )

2025-05-09 10:01:49 +00:00

scalar_type.py

[Misc] Fix ScalarType float4 naming (#17690 )

2025-05-06 01:07:15 -07:00

scripts.py

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

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

sequence.py

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663 )

2025-05-27 01:44:20 -07:00

test_utils.py

[Misc] replace does not exist model (#18119 )

2025-05-14 02:13:47 -07:00

tracing.py

Update deprecated Python 3.8 typing (#13971 )

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

utils.py

[Perf] API-server scaleout with many-to-many server-engine comms (#17546 )

2025-05-30 08:17:00 -07:00

version.py

[Metrics] Hide deprecated metrics (#15458 )

2025-04-02 07:37:19 -07:00