5 people 0d2689e0df [ROCm][Perf] Skip redundant sparse index remap on non-indexer layers (#51309) ...

Signed-off-by: Sriram Kumar <sriramkumar.kishorekumar@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Simon Danielsson <70206058+simondanielsson@users.noreply.github.com>

2026-10-13 05:25:56 +00:00

..

basic_correctness

[MRV2] Switch CI tests still running on MRV1 unnecessarily (#61014)

2026-10-11 09:57:07 -07:00

benchmarks

[Frontend] Support min_p in the Responses API (#48084)

2026-10-08 20:38:17 +00:00

compile

[ROCm][Perf] Fix Gemma AR+RMS prefill fallback (#58547)

2026-10-12 19:53:08 +00:00

config

[Bugfix][GLM-5.3-Flash] Restore MTP index sharing across draft iterations (#61079)

2026-10-12 05:41:52 +00:00

cuda

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

detokenizer

[Bugfix][Spec Decode] Trim token_ids/logprobs left past a stop string under speculative decoding (#47616)

2026-10-09 14:22:31 -07:00

device_allocator

[Bugfix] Don't drop the rest of the allocator config when toggling expandable segments (#57982)

2026-09-25 17:34:19 -05:00

distributed

[ROCm][Perf] Fix Gemma AR+RMS prefill fallback (#58547)

2026-10-12 19:53:08 +00:00

engine

[Perf] Support minimum KV splits configuration for TokenSpeed MLA decode (#60345)

2026-10-09 23:33:47 +00:00

entrypoints

[Rust Frontend] Add per-request timing metrics to chat and completions (#59314)

2026-10-12 15:39:10 -07:00

evals

[Bugfix] [Spec Decode] DeepSeek V4/V4.1 NVFP4: keep ignored MTP/DSpark experts on MXFP4 (#59655)

2026-10-08 00:10:32 +00:00

fusion

[Fusion] Support 3D activation quantization fusion and enable it for Pixtral (#59612)

2026-10-09 15:12:03 +08:00

ir

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

jit_monitor

[Perf] JIT monitor: hook TileLang JITImpl.compile instead of __call__ (#58685)

2026-10-08 00:11:59 +00:00

kernels

[ROCm][Perf] Skip redundant sparse index remap on non-indexer layers (#51309)

2026-10-13 05:25:56 +00:00

lora

[Bugfix][LoRA] Apply PEFT rank_pattern / alpha_pattern scaling per module (#59801)

2026-10-12 21:49:30 +08:00

model_executor

[Model Loader] Make dummy weight init dtype-aware (#61134)

2026-10-12 18:33:26 -07:00

models

[Core][Refactor] Move KV cache planning logic to kv_cache_planning.py (#61183)

2026-10-13 03:05:39 +00:00

multimodal

[Model] Support Cloudflare/clef-omni on /v1/systemone (#61064)

2026-10-12 21:27:34 +08:00

parser

[Bugfix] Accept whole-number floats for integer tool arguments in the response parser (#61297)

2026-10-13 12:55:20 +08:00

platforms

[Attention] Remove cascade attention (#61126)

2026-10-12 10:41:07 -07:00

plugins

[Bugfix][Platform] Don't resolve current_platform during import vllm (#60766)

2026-10-12 17:05:34 +00:00

plugins_tests

[Bugfix][Platform] Don't resolve current_platform during import vllm (#60766)

2026-10-12 17:05:34 +00:00

prompts

…

quantization

[XPU] bump up auto-round-lib to 0.16.0 (#60976)

2026-10-12 14:47:59 +08:00

reasoning

[Frontend] Port Step-3.5 parsers to the streaming parser engine (#59321)

2026-10-01 22:18:37 +00:00

renderers

[Test][Renderer] Cover the reasoning -> reasoning_content mirror in chat message parsing (#56129)

2026-10-13 03:58:32 +00:00

rocm

[ROCm][CI] Add test coverage for VLLM_ROCM_MOE_PADDING memory-stride padding transparency (#59332)

2026-10-02 11:23:22 -05:00

samplers

[watermark] compatibility validation (#56801)

2026-10-05 14:37:13 -04:00

spec_decode

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

standalone_tests

[CI] Add nightly Python 3.14 smoke test (#60456)

2026-10-12 10:11:26 -07:00

tokenizers_

[Bugfix] Preserve independent tokenizer code_revision in snapshot resolution (#61272)

2026-10-13 04:23:45 +00:00

tool_parsers

[Frontend] Support CustomToolCall in the non-Harmony Responses API (#57322)

2026-10-12 17:22:55 +08:00

tool_use

[Frontend] Support CustomToolCall in the non-Harmony Responses API (#57322)

2026-10-12 17:22:55 +08:00

tools

[Agents] Add pre-commit check for agent files and skills (#59657)

2026-10-02 09:38:22 -07:00

tracing

[Refactor] Remove dead tests code (#58916)

2026-09-30 04:39:03 +00:00

transformers_utils

[Performance] Load HF tokenizers and processors from a local snapshot (#60825)

2026-10-12 13:45:54 +00:00

utils_

[Bugfix] Scope deprecated CLI argument warnings to the parser that defines them (#59917)

2026-10-08 15:29:04 +00:00

v1

[ROCm][Perf] Skip redundant sparse index remap on non-indexer layers (#51309)

2026-10-13 05:25:56 +00:00

vllm_test_utils

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

watermarking

[Metrics] Count finished requests by watermark status (#58715)

2026-10-12 17:21:22 +00:00

__init__.py

…

ci_envs.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

conftest.py

[Attention] Remove cascade attention (#61126)

2026-10-12 10:41:07 -07:00

test_attention_backend_registry.py

[Platform] Allow BackendEnum dynamic register (#41091)

2026-10-08 09:56:19 +08:00

test_audio_media_size_precheck.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_cmake_utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_config.py

[Qwen4Exp] support Sequence Parallelism for Qwen3.8-Flash-Next (#56322)

2026-10-12 20:56:44 +08:00

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

[Security] Fix P2P ZMQ socket exhaustion via unbounded peer sessions (#51504)

2026-10-11 11:39:11 -04:00

test_force_first_config.py

…

test_fxgraphcache_pickle_patch.py

…

test_logger.py

[Core][Logging] Add built-in JSON formatter (#58739)

2026-10-01 09:11:46 +01:00

test_logprobs.py

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

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

test_outputs.py

[Bugfix][Core] Preserve speculative metrics when coalescing outputs (#55708)

2026-10-07 08:35:14 +08:00

test_pcp_dp.py

[PCP] Support prefill context parallelism with data parallelism (#57075)

2026-09-23 22:32:36 -04:00

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

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

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

test_ray_env.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_regression.py

…

test_request_input_bounds.py

[CI] Allowlist-shrink batch 1: wire 17 root-level tests + drop 5 stale watermarking entries into misc.yaml (#58055)

2026-09-27 22:23:46 -07:00

test_sampling_params.py

[watermark] compatibility validation (#56801)

2026-10-05 14:37:13 -04:00

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

[CI] Allowlist-shrink batch 1: wire 17 root-level tests + drop 5 stale watermarking entries into misc.yaml (#58055)

2026-09-27 22:23:46 -07:00

test_uvicorn_logging.py

[Core][Logging] Add built-in JSON formatter (#58739)

2026-10-01 09:11:46 +01:00

test_version.py

[CI] Allowlist-shrink batch 1: wire 17 root-level tests + drop 5 stale watermarking entries into misc.yaml (#58055)

2026-09-27 22:23:46 -07:00

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

[CI] Allowlist-shrink batch 2: wire 9 tests/models/ files into Buildkite, fix 2 stale bugs found (#59050)

2026-10-06 21:16:53 -07:00

test_zentorch_version_pin.py

[ZenCPU][Test] Add zentorch/torch version pin consistency test (#52888)

2026-10-06 13:12:19 +08:00

utils.py

[MRV2] Switch CI tests still running on MRV1 unnecessarily (#61014)

2026-10-11 09:57:07 -07:00