vLLM/vllm at 12a223ef9bfebcc61e477047dce049495fe8c8a8 - vLLM

adapter_commons

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

assets

[Bugfix] Fix ndarray video color from VideoAsset (#21064 )

2025-07-19 02:17:16 -07:00

attention

update flashinfer to v0.2.9rc1 (#21485 )

2025-07-24 14:06:11 -07:00

benchmarks

[bugfix] fix profile impact benchmark results (#21507 )

2025-07-27 22:44:24 -07:00

compilation

[XPU] Conditionally import CUDA-specific passes to avoid import errors on xpu platform (#21036 )

2025-07-24 23:23:36 +08:00

core

[V0 Deprecation] Remove Prompt Adapters (#20588 )

2025-07-23 16:36:48 -07:00

device_allocator

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

distributed

skip fusedmoe layer for start_load_kv (#21378 )

2025-07-28 18:59:44 -07:00

engine

Use metavar to list the choices for a CLI arg when custom values are also accepted (#21760 )

2025-07-28 19:31:10 +00:00

entrypoints

[Bugfix] Improve JSON extraction in LlamaToolParser (#19024 )

2025-07-28 12:36:58 +00:00

executor

[V1] Get supported tasks from model runner instead of model config (#21585 )

2025-07-25 05:36:45 -07:00

inputs

[V0 Deprecation] Remove Prompt Adapters (#20588 )

2025-07-23 16:36:48 -07:00

logging_utils

[BugFix] Don't catch BaseException when dumping execute_model errors (#19626 )

2025-06-16 11:01:08 +00:00

lora

[XPU] IPEX-optimized Punica Wrapper on XPU (#21703 )

2025-07-28 16:43:37 +00:00

model_executor

[Refactor] Merge Compressed Tensor FP8 CompressedTensorsW8A8Fp8MoEMethod and CompressedTensorsW8A8Fp8MoECutlassMethod (#21775 )

2025-07-28 19:47:21 -06:00

multimodal

[Core][Model] PrithviMAE Enablement on vLLM v1 engine (#20577 )

2025-07-23 11:00:23 -07:00

platforms

[XPU] IPEX-optimized Punica Wrapper on XPU (#21703 )

2025-07-28 16:43:37 +00:00

plugins

[V0 deprecation] Remove V0 HPU backend (#21131 )

2025-07-17 16:37:36 -07:00

profiler

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

ray

[Misc] Copy HF_TOKEN env var to Ray workers (#21406 )

2025-07-22 16:18:42 -07:00

reasoning

remove GLM-4.5 quantization wrong Code (#21435 )

2025-07-24 01:52:43 -07:00

third_party

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

transformers_utils

[Bugfix] Mistral crashes on tool with no description (#21167 )

2025-07-28 08:03:35 -07:00

triton_utils

[Bugfix] Add missing field to TritonLanguagePlaceholder (#20812 )

2025-07-11 05:25:11 -07:00

usage

[Misc] Add logger.exception for TPU information collection failures (#20510 )

2025-07-05 07:24:32 -07:00

utils

[Bugfix] DeepGEMM is not enabled on B200 due to _lazy_init() (#21472 )

2025-07-28 20:51:22 +00:00

v1

Revert "[V1] Exception Handling when Loading KV Cache from Remote Store" (#21778 )

2025-07-28 20:15:18 +00:00

vllm_flash_attn

[BugFix] Fix vllm_flash_attn install issues (#17267 )

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

worker

[V1] Get supported tasks from model runner instead of model config (#21585 )

2025-07-25 05:36:45 -07:00

__init__.py

[Perf][CLI] Improve overall startup time (#19941 )

2025-06-22 23:11:22 +00:00

_custom_ops.py

[Bug] Enforce contiguous input for dynamic_scaled_fp8_quant and static_scaled_fp8_quant (#21773 )

2025-07-28 19:55:48 +00:00

_ipex_ops.py

[FIX][Intel GPU]fix ipex flash_attn_varlen_func api missing parameter (#20348 )

2025-07-01 22:26:40 -07:00

beam_search.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

collect_env.py

[Misc] Refactor: Improve argument handling for conda command (#20481 )

2025-07-15 19:43:19 -07:00

config.py

[Perf] Disable chunked local attention by default with llama4 (#21761 )

2025-07-28 18:49:04 -04:00

connections.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

env_override.py

[Misc] Reduce warning message introduced in env_override (#19476 )

2025-06-11 17:29:54 +08:00

envs.py

[Perf] Disable chunked local attention by default with llama4 (#21761 )

2025-07-28 18:49:04 -04:00

forward_context.py

[CUDA] Enable full cudagraph for FlashMLA (#18581 )

2025-06-13 18:12:26 +00:00

jsontree.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

logger.py

[Attention] MLA - Flashinfer Ragged Prefill (#20034 )

2025-07-10 20:17:47 -07:00

logits_process.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

outputs.py

[Model][2/N] Automatic conversion of CrossEncoding model (#19978 )

2025-07-03 13:59:23 +00:00

pooling_params.py

[V1] Get supported tasks from model runner instead of model config (#21585 )

2025-07-25 05:36:45 -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

[Deprecation] Remove everything scheduled for removal in v0.10.0 (#20979 )

2025-07-15 15:57:53 +00:00

scalar_type.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

scripts.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

sequence.py

Revert "[V1] Exception Handling when Loading KV Cache from Remote Store" (#21778 )

2025-07-28 20:15:18 +00:00

tasks.py

[V1] Get supported tasks from model runner instead of model config (#21585 )

2025-07-25 05:36:45 -07:00

test_utils.py

Simplify weight loading in Transformers backend (#21382 )

2025-07-22 20:29:43 -07:00

tracing.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

version.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00