Xingyu Liu 9845589af5

Merge branch 'main' into model_arch_cfg ...

Signed-off-by: Xingyu Liu <38244988+charlotte12l@users.noreply.github.com>

2025-12-10 20:35:30 -08:00

..

basic_correctness

[ROCm][CI] Fix test_max_len.py for Rocm (#29916)

2025-12-08 16:58:30 -05:00

benchmarks

Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)

2025-12-02 20:40:56 +00:00

compile

[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)

2025-12-10 19:59:35 -08:00

config

refactor tests

2025-12-09 23:29:32 -08:00

cuda

…

detokenizer

…

distributed

[DCP][Bugfix][CI] Fix accuracy issue of DCP when using FLASH_ATTN_MLA (#30309)

2025-12-09 08:22:14 +00:00

engine

[Frontend] Remap -O to -cc commandline flag (#29557)

2025-11-28 21:51:12 +00:00

entrypoints

[P/D] KV Load Failure Recovery/Abort Configuration (#26813)

2025-12-10 11:00:52 -08:00

evals

Add output token counting to gsm8k eval (#28594)

2025-11-14 09:32:03 +00:00

kernels

[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)

2025-12-10 19:59:35 -08:00

lora

Lora MoE Align Improvements (#29257)

2025-12-09 10:35:16 +08:00

model_executor

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

models

Merge branch 'main' into model_arch_cfg

2025-12-10 10:16:26 -08:00

multimodal

[ROCm][CI] Attempt to fix the failures under a subgroup of the e2e the test group (#29358)

2025-12-10 05:33:13 +00:00

plugins

[v1] Add PrefixLM support to FlexAttention backend (#27938)

2025-12-07 15:51:36 +00:00

plugins_tests

[Frontend] Resettle pooling entrypoints (#29634)

2025-12-01 15:30:43 +08:00

prompts

…

quantization

[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)

2025-12-10 19:59:35 -08:00

reasoning

[Structured Output][Reasoning] Improves decoding throughput for models using single-token reasoning endings. (#30056)

2025-12-09 18:54:08 +08:00

rocm/aiter

[Bugfix] [ROCm] [AITER]: Fix aiter block quant not compatible with torch compile dynamo (#28716)

2025-11-14 10:30:50 -08:00

samplers

[Core] Switch Flat logprob control from environment variable to SamplingParams (#28914)

2025-11-19 02:10:02 +00:00

standalone_tests

[CI] fix docker image build by specifying merge-base commit id when downloading pre-compiled wheels (#29930)

2025-12-03 14:08:19 -08:00

system_messages

…

tokenizers_

Add Mistral Large 3 and Ministral 3 (#29757)

2025-12-02 10:29:00 +00:00

tool_use

[BUGFIX] Mistral tool call parser v11+ (#30332)

2025-12-09 14:55:38 +00:00

tools

…

tpu

…

transformers_utils

[Chore]: Reorganize gguf utils funtions under transformers_utils (#29891)

2025-12-02 17:33:23 +00:00

utils_

[Frontend] Remove confusing -O.xx flag error (#30169)

2025-12-07 02:53:42 +00:00

v1

[Chore] Fix torch precision warning (#30428)

2025-12-11 04:05:56 +00:00

vllm_test_utils

…

weight_loading

[ROCm][CI] Fix Weight Loading With Multiple GPU Tests on ROCm (#28984)

2025-11-19 21:31:33 +00:00

__init__.py

…

ci_envs.py

…

conftest.py

[Deprecation] Remove deprecated task, seed and MM settings (#30397)

2025-12-10 19:59:39 -08:00

test_config.py

Merge branch 'main' into model_arch_cfg

2025-12-10 20:35:30 -08:00

test_embedded_commit.py

…

test_envs.py

[Perf] Enable environment cache in EngineCore to enable the feature for UniProcExecutor as well (#29289)

2025-12-10 14:13:01 -05:00

test_inputs.py

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

test_logger.py

[BugFix] respect VLLM_LOGGING_LEVEL in logger (#29761)

2025-12-02 07:49:16 +00:00

test_logprobs.py

[Core] Switch Flat logprob control from environment variable to SamplingParams (#28914)

2025-11-19 02:10:02 +00:00

test_outputs.py

…

test_pooling_params.py

…

test_regression.py

…

test_routing_simulator.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

utils.py

[Deprecation] Remove deprecated task, seed and MM settings (#30397)

2025-12-10 19:59:39 -08:00