qizixiandLu Fang 5bfe0dea7a [bug fix] Fix llama4 spec decoding (#22691) ...

Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>

2025-08-19 08:53:24 +00:00

..

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

[V0 Deprecation] Remove V0 FlashInfer attention backend (#22776)

2025-08-18 19:54:16 -07:00

benchmarks

[Misc] Add request_id into benchmark_serve.py (#23065)

2025-08-19 08:32:18 +00:00

compilation

chore: disable enable_cpp_symbolic_shape_guards (#23048)

2025-08-18 23:08:05 -04:00

config

[XPU] Fix compile size for xpu (#23069)

2025-08-18 00:04:08 -07:00

core

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

device_allocator

[Misc] Add SPDX-FileCopyrightText (#19100)

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

distributed

[TPU] make ptxla not imported when using tpu_commons (#23081)

2025-08-19 11:46:42 +08:00

engine

[Hardware][IBM Z]Enable v1 for s390x and s390x dockerfile fixes (#22725)

2025-08-19 04:40:37 +00:00

entrypoints

fix: OpenAI SDK compat (ResponseTextConfig) (#23126)

2025-08-18 15:22:59 -07:00

executor

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

inputs

[Refactor] Defer tensor data construction in MultiModalKwargs (#23030)

2025-08-16 21:05:50 -07:00

logging_utils

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

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

lora

[Bugfix] Fix: Fix multi loras with tp >=2 and LRU cache (#20873)

2025-07-31 19:48:13 -07:00

model_executor

[bug fix] Fix llama4 spec decoding (#22691)

2025-08-19 08:53:24 +00:00

multimodal

[Refactor] Get prompt updates earlier (#23097)

2025-08-18 12:31:53 +00:00

platforms

[Hardware][IBM Z]Enable v1 for s390x and s390x dockerfile fixes (#22725)

2025-08-19 04:40:37 +00:00

plugins

[XPU] upgrade torch 2.8 on for XPU (#22300)

2025-08-08 17:03:45 -07:00

profiler

[Misc] Add SPDX-FileCopyrightText (#19100)

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

ray

[Misc] Getting and passing ray runtime_env to workers (#22040)

2025-08-01 23:54:40 -07:00

reasoning

[Frontend] Avoid list copies in serving_chat.py (#22947)

2025-08-16 02:06:30 +00:00

third_party

[Misc] Add SPDX-FileCopyrightText (#19100)

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

transformers_utils

chore: remove unnecessary patch_padding_side for the chatglm model (#23090)

2025-08-18 12:32:13 +00:00

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

[V1] Logits processors extensibility (#19912)

2025-08-16 12:59:17 -07:00

v1

[Log] Warning Once for Cutlass MLA (#23137)

2025-08-18 23:24:16 -07:00

vllm_flash_attn

[BugFix] Fix vllm_flash_attn install issues (#17267)

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

worker

[V0 Deprecation] Remove advance_step (#22969)

2025-08-15 08:22:31 -07:00

__init__.py

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

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

_custom_ops.py

[Kernel/Quant] Remove AQLM (#22943)

2025-08-16 19:38:21 +00:00

_ipex_ops.py

[XPU]Fix flash_attn_varlen_func interface on xpu (#22350)

2025-08-06 19:28:11 -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

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

[Bugfix] Added more env vars to hash (#22449)

2025-08-15 20:08:37 +00:00

forward_context.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

logger.py

Optimize logger init performance by using module-level constants (#22373)

2025-08-06 20:32:19 -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

Support token_type_ids in V1 with less code changes (#21985)

2025-08-10 22:54:59 -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

[Docs] Fix warnings in docs build (#22588)

2025-08-10 05:49:51 -07:00

scalar_type.py

[Kernel] [Quantization] Add MXFP4 and bias support for marlin kernel (#22428)

2025-08-14 11:23:22 -07:00

scripts.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

sequence.py

[Bugfix] fix IntermediateTensors equal method (#23027)

2025-08-18 02:58:11 -07:00

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

[Misc] Modify the organization of GLM series (#22171)

2025-08-03 23:51:20 -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