AusarandClaude 6bafc049aa [Bugfix][PP] Never drop a decoding request from the sampled-token broadcast (#54436) ...

Signed-off-by: ArcheyChen <45146080+ArcheyChen@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-08-31 23:49:54 +00:00

..

basic_correctness

[CI][Test] Deflake test_mem.py sleep-mode asserts via allocator bookeeping (#54312)

2026-08-29 12:05:17 -07:00

benchmarks

[Bugfix] Restore multimodal support on the plain "vllm" throughput backend (#52168)

2026-08-28 10:28:25 +00:00

compile

[Test][Qwen3-VL] Cover compiled DeepStack input contract (#53529)

2026-08-31 10:46:50 +00:00

config

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

cuda

…

detokenizer

…

distributed

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

engine

[Frontend] Move cli_args.py and dp_supervisor.py out openai folder (#53659)

2026-08-25 07:02:32 +00:00

entrypoints

[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management (#49445)

2026-08-31 14:26:49 +00:00

evals

Add Laguna-XS-2.1-INT4 to nightly CI (#52961)

2026-08-31 14:22:00 -04:00

fusion

…

ir

…

jit_monitor

…

kernels

[Kernel][Gemma4] Prune Triton sliding-window tiles for multimodal prefixes (#53147)

2026-08-31 22:21:22 +00:00

lora

[Misc] Use VLLMValidationError in offline inference input validation (#53432)

2026-08-23 08:43:51 -07:00

model_executor

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

models

[Kimi-K3][Perf] Make native CUDA AttnRes the SM100 default (#54261)

2026-08-31 23:18:12 +00:00

multimodal

[Bugfix][Multimodal] Honor modality-scoped mm_processor_kwargs (#53808)

2026-08-31 06:37:12 +00:00

parser

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

platforms

[CPU] Support FP16/BF16 persisted GDN state on AMX (#52191)

2026-08-31 16:32:20 +08:00

plugins

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

plugins_tests

[Frontend] Move cli_args.py and dp_supervisor.py out openai folder (#53659)

2026-08-25 07:02:32 +00:00

prompts

…

quantization

[AutoRound] Support AutoRound Format Block-Wise FP8 in vLLM (#47434)

2026-08-31 22:56:20 +08:00

reasoning

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

renderers

[Bugfix][Frontend] Truncate prompt_is_token_ids with the prompt (#54509)

2026-08-31 09:29:01 +00:00

samplers

…

spec_decode

…

standalone_tests

…

system_messages

…

tokenizers_

[Bugfix][Tokenizer] Replace bare asserts in the DeepSeek V4 encoder (#53747)

2026-08-25 16:30:23 +00:00

tool_parsers

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

tool_use

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

tools

[Rocm][CI] add dockerfile.xpu to rocm ci artifact (#53949)

2026-08-27 01:06:48 -07:00

tracing

…

transformers_utils

[Bugfix][Model] Fix K3 DSpark config for 96-head drafts (#54005)

2026-08-27 15:58:28 -07:00

utils_

[Model] Remove ten deprecated model architectures (#53608)

2026-08-24 17:06:00 -07:00

v1

[Bugfix][PP] Never drop a decoding request from the sampled-token broadcast (#54436)

2026-08-31 23:49:54 +00:00

vllm_test_utils

…

weight_loading

[Model] Remove ten deprecated model architectures (#53608)

2026-08-24 17:06:00 -07:00

__init__.py

…

ci_envs.py

…

conftest.py

[Bugfix][CPU] Fix several bugs (#54042)

2026-08-31 15:33:06 +08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_audio_media_size_precheck.py

fix(security): enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB on all audio paths (#53561)

2026-08-24 21:37:02 +00:00

test_cmake_utils.py

…

test_config.py

[Nixl][PD] DCP support for MLA models (#50611)

2026-08-29 16:03:53 +00:00

test_connections.py

Reject oversized media before fully downloading it (#51896)

2026-08-24 01:15:09 +00:00

test_embedded_commit.py

…

test_envs.py

…

test_force_first_config.py

…

test_fxgraphcache_pickle_patch.py

…

test_logger.py

…

test_logprobs.py

[Bugfix] Handle empty FlatLogprobs slices and delta output (#53704)

2026-08-26 21:00:54 +08:00

test_outputs.py

…

test_pooling_params.py

…

test_quantization_revision_pin.py

…

test_ray_env_utils.py

[Bugfix] Set breakable graph env before Ray actor import (#53293)

2026-08-28 23:11:50 +00:00

test_ray_env.py

…

test_regression.py

…

test_request_input_bounds.py

[Bugfix] Reject empty bad-word tokenizations (#53433)

2026-08-31 12:07:17 -07:00

test_sampling_params.py

…

test_scalartype.py

…

test_sequence.py

…

test_tensorizer_revision_pin.py

…

test_triton_utils.py

Exclude the cpu backend from vLLM's active-Triton-driver count (#53530) (#53530)

2026-08-25 04:13:13 +00:00

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

…

utils.py

[CI] Harden RemoteVLLMServer GPU cleanup checks (#52282)

2026-08-19 14:17:17 -05:00