4 people 1b079c40ff [Bugfix][Model Runner V2][Spec Decode] Fix off-by-one in bad_words draft-prefix matching (#52311) ...

Signed-off-by: jyan <r_02213@sjtu.edu.cn>
Co-authored-by: jyan <r_02213@sjtu.edu.cn>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-16 09:02:20 +00:00

..

basic_correctness

[Perf] Avoid some more unnecessary GPU<->CPU syncs (#51458)

2026-08-08 17:13:26 -07:00

benchmarks

[MISC][Bench] refactor throughput and reuse serve's get samples (#50981)

2026-08-06 10:31:23 +00:00

compile

[Kernel][Perf] Add fused CUDA post-conv MTP decode kernel for Qwen3.5 GDN (#51674)

2026-08-14 11:44:45 +08:00

config

[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)

2026-08-13 16:22:29 -07:00

cuda

[Bugfix][Platform] Stop re-initializing NVML on every device-capability check (fixes #50381) (#50393)

2026-08-07 08:30:00 +00:00

detokenizer

[Bugfix][Spec Decode] Select earliest-completing stop string in check_stop_strings (#49391)

2026-07-23 18:14:06 +08:00

distributed

fix and test EPLB balancedness calculation (#51813)

2026-08-12 20:27:22 -07:00

engine

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

entrypoints

[Bugfix][Anthropic] Return 4xx for client-caused errors in /v1/messages (#52246)

2026-08-16 01:05:17 -07:00

evals

[CI] Shard Humming H100 eval (#52326)

2026-08-14 15:12:02 -07:00

fusion

Add the QuantizedActivation linear-kernel contract (#44260)

2026-06-12 13:48:15 -07:00

ir

[Perf] Set IR Op Priority Once at Worker Init (#42631)

2026-05-15 15:56:13 +00:00

jit_monitor

[ROCm] Defer tilelang import through its import from vllm.tilelang_utils import tilelang and relaxed has_tilelang (#51159)

2026-08-13 13:12:40 -05:00

kernels

[Bugfix][DSv4] Revert adaptive C128A metadata packing (#51318)

2026-08-15 18:39:23 -07:00

lora

[Test][LoRA] Speed up the LoRA test job (#52331)

2026-08-14 12:08:41 -05:00

model_executor

[UT][XPU] fix b12x UT (#52265)

2026-08-14 09:49:47 -04:00

models

[Core] Check for GPU<->CPU syncs during CI (#43107)

2026-08-14 17:42:05 -07:00

multimodal

[Frontend] Consolidate entrypoint exception handler (#52261)

2026-08-14 09:27:24 +00:00

parser

[Frontend] Support count_reasoning_tokens in the Streaming Parser Engine (#45802)

2026-08-15 06:51:14 -07:00

plugins

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

plugins_tests

[Migration] Migrate bitsandbytes support to OOT plugin (#43529)

2026-08-09 10:27:31 +08:00

prompts

…

quantization

[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)

2026-08-14 09:47:55 -04:00

reasoning

chore: Upstream Cohere parser fixes + tests (#51998)

2026-08-13 05:05:36 -07:00

renderers

[Frontend] Consolidate entrypoint exception handler (#52261)

2026-08-14 09:27:24 +00:00

rocm/aiter

[ROCm][CI] Add aiter per-token FP8 quant roundtrip and RMSNorm determinism tests (#50905)

2026-08-04 21:32:08 -05:00

samplers

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)

2026-08-11 14:19:16 -04:00

spec_decode

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

standalone_tests

Detect ROCm wheel variant from environment for precompiled wheels. (#49365)

2026-08-13 21:19:20 -07:00

system_messages

…

tokenizers_

[Frontend] DeepSeek V4 0731 reasoning effort prompts & mappings (#50580)

2026-08-04 08:51:32 -07:00

tool_parsers

chore: Upstream Cohere parser fixes + tests (#51998)

2026-08-13 05:05:36 -07:00

tool_use

Add Muse Glimmer model support (#51655)

2026-08-14 12:28:56 +08:00

tools

[ROCm][CI] Reuse equivalent ROCm CI images (#48646)

2026-08-09 01:25:03 -07:00

tracing

…

transformers_utils

Add Muse Glimmer model support (#51655)

2026-08-14 12:28:56 +08:00

utils_

[Frontend] Add routed-experts prompt offset (#51906)

2026-08-13 08:09:00 -07:00

v1

[Bugfix][Model Runner V2][Spec Decode] Fix off-by-one in bad_words draft-prefix matching (#52311)

2026-08-16 09:02:20 +00:00

vllm_test_utils

…

weight_loading

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

__init__.py

…

ci_envs.py

…

conftest.py

[Migration] Migrate bitsandbytes support to OOT plugin (#43529)

2026-08-09 10:27:31 +08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_cmake_utils.py

[CI/Build] Add warning for unsupported global PTX architecture requests in... (#51901)

2026-08-15 07:01:52 -07:00

test_config.py

[Bugfix] Pick the DeepSeek V4 eager cudagraph region per model runner (#52401)

2026-08-15 21:04:08 -07:00

test_embedded_commit.py

…

test_envs.py

[Kernel][Perf] Add fused CUDA post-conv MTP decode kernel for Qwen3.5 GDN (#51674)

2026-08-14 11:44:45 +08:00

test_force_first_config.py

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

2026-06-16 15:16:45 +02:00

test_fxgraphcache_pickle_patch.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205)

2026-04-10 08:29:35 +00:00

test_inputs.py

…

test_logger.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_quantization_revision_pin.py

Preserve revision pins in secondary artifact loaders (#51446)

2026-08-11 04:33:10 +00:00

test_ray_env_utils.py

[Feat][Executor] Introduce RayExecutorV2 (#36836)

2026-04-01 14:34:29 -07:00

test_ray_env.py

fix nixl side-channel host selection (#41806)

2026-05-11 07:40:37 +00:00

test_regression.py

[CI/Build] Use modelscope's international site for regression test (#42176)

2026-05-09 19:47:09 -07:00

test_request_input_bounds.py

Bound generation inputs before expensive work (#51447)

2026-08-11 22:03:50 +08:00

test_sampling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_scalartype.py

…

test_sequence.py

…

test_tensorizer_revision_pin.py

Preserve revision pins in secondary artifact loaders (#51446)

2026-08-11 04:33:10 +00:00

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

[ROCm][CI] Select CPU platform for native no-GPU jobs (#49515)

2026-08-14 23:30:56 -07:00

utils.py

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)

2026-08-11 14:19:16 -04:00