1Cat-vLLM

basic_correctness

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

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

benchmarks

[Bugfix] Fail instead of ignoring when CompilationConfig gets invalid args (#30708 )

2025-12-15 20:18:02 +00:00

compile

[CI/Build] Fix compatibility between #30244 and #30396 (#30787 )

2025-12-16 20:21:19 -08:00

config

[torch.compile] caching of config fields should be opt-out by default (#26468 )

2025-11-19 06:13:54 -08:00

cuda

…

detokenizer

…

distributed

[EPLB] Support EPLB w/ NVFP4 (#29804 )

2025-12-11 22:59:40 +00:00

engine

fix: enhance human_readable_int function (#30337 )

2025-12-10 23:30:33 -08:00

entrypoints

[Frontend] Add max-completion-token option to transcription/translation endpoints (#30769 )

2025-12-16 19:36:49 +00:00

evals

[CI] Generalize gsm8k test args and add Qwen3-Next MTP B200 test (#30723 )

2025-12-16 14:28:34 -05:00

kernels

CustomOp: grouped topk (#29575 )

2025-12-17 17:43:00 +08:00

lora

Fix instantiation of HfHubHTTPError in LoRA test (#30768 )

2025-12-16 08:02:24 -08:00

model_executor

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

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

models

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475 )

2025-12-16 14:18:17 -08:00

multimodal

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475 )

2025-12-16 14:18:17 -08:00

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

[Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484 )

2025-12-12 19:34:23 -08:00

reasoning

[Chore] Adjust tokenizer import to avoid circular imports (#30601 )

2025-12-13 04:42:39 -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

improve lazy import test (#30733 )

2025-12-16 03:12:05 +00:00

system_messages

…

tokenizers_

[Refactor] TokenizerRegistry only uses lazy imports (#30609 )

2025-12-13 23:16:22 +08:00

tool_parsers

[Refactor] [3/N] Move tool parser tests and run on CPU (#30693 )

2025-12-15 13:45:36 +00:00

tool_use

[Bugfix][Frontend] Prevent IndexError in MiniMax M2 tool parser during streaming extraction (#30555 )

2025-12-17 16:37:57 +08:00

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

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475 )

2025-12-16 14:18:17 -08:00

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

[CI] Whisper logprobs tests (#30504 )

2025-12-13 10:49:11 +08:00

test_config.py

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

2025-12-10 19:59:39 -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

Improve parse_raw_prompt test cases for invalid input .v2 (#30512 )

2025-12-14 11:18:41 +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