Jiahan Chang (Cyrus) d0975a4b50 [perf] Add gemma RMS AR fusion (#42646) ...

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-06-04 01:33:59 -07:00

..

basic_correctness

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

benchmarks

[Benchmark] Enable reasoning-model (thinking) benchmarking via --chat-template-kwargs for client-rendered datasets (#44244)

2026-06-02 22:49:51 -07:00

compile

[perf] Add gemma RMS AR fusion (#42646)

2026-06-04 01:33:59 -07:00

config

[Perf] FP8 FlashInfer Attn for ViT (#38065)

2026-04-27 13:44:15 +08:00

cuda

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

detokenizer

[CI/Build] Remove use of skip_v1 (#34699)

2026-02-18 12:19:11 +08:00

distributed

[EPLB] Nixl communicator optimization. Zero-copy transfers (#41633)

2026-06-04 03:40:34 +00:00

engine

[BugFix] HFValidationError with cloud storage URIs when HF_HUB_OFFLINE=1 (#39155)

2026-05-27 10:53:32 -05:00

entrypoints

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

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

evals

[CI] Add DSV4-Flash to gsm8k moe-refactor/config-b200.txt (#42111)

2026-05-19 20:21:01 -07:00

ir

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

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

kernels

[EPLB] Nixl communicator optimization. Zero-copy transfers (#41633)

2026-06-04 03:40:34 +00:00

lora

[Bugfix] Vendor MiniCPMV/MiniCPMO processors to unblock Transformers v5 (#44282)

2026-06-02 07:14:38 -07:00

model_executor

[ROCm][CI] Skip fp8 reload tests on gfx90a (MI250) (#44369)

2026-06-02 22:27:14 -05:00

models

[MM][Perf][CG] Support ViT full CUDA graph for InternVL (#41759)

2026-06-04 10:24:25 +08:00

multimodal

[Multimodal] Automatically select registered video loader for VLM (#44126)

2026-06-02 09:09:47 +00:00

parser

[Bugfix] Honor tool_choice="none" in Chat Completions streaming (#42752)

2026-06-03 13:27:45 -07:00

plugins

[Misc] Reorganize inputs (#35182)

2026-03-25 10:22:54 -07:00

plugins_tests

[CI/Build] Skip Prithvi/Terratorch model-registry tests when terratorch is missing (#41389)

2026-04-30 12:47:55 -07:00

prompts

…

quantization

[Kernel][MoE] Add GELU_TANH to CPU, CUTLASS, and WNA16 MoE backends (#42027)

2026-06-02 17:12:08 -04:00

reasoning

[Bugfix] KimiK2ReasoningParser: guard against buffered end-token in streaming (#41068)

2026-05-04 17:42:05 +00:00

renderers

[Frontend][Responses API] Move developer-to-system conversion into HF renderer (#43590)

2026-06-03 14:52:24 +00:00

rocm/aiter

[ROCm][CI] Cleaning and restructuring amd-ci legacy pipeline (#34839)

2026-03-19 14:30:58 -05:00

samplers

[Frontend] Add Support for MM Encoder/Decoder Beam Search (Offline) (#36153)

2026-03-06 01:16:56 -08:00

spec_decode

[Feature] Support custom callable proposer backend for speculative decoding (#39487)

2026-05-13 16:53:01 +00:00

standalone_tests

Add structure to requirements/ directory (#39024)

2026-04-10 13:46:41 -07:00

system_messages

…

tokenizers_

[CI] De-flake renderers/test_hf.py::test_resolve_content_format_fallbacks[Qwen/Qwen-VL-string] (#43064)

2026-05-22 12:15:22 +08:00

tool_parsers

[CI] Stabilize OpenAI schema fuzzing for malformed structural tags (#44131)

2026-06-01 19:56:15 -07:00

tool_use

[Misc] Use VLLMValidationError consistently in chat completion and completion protocol validators (#36254)

2026-06-01 04:04:11 +00:00

tools

build: embed image provenance metadata in vLLM containers (#40653)

2026-04-29 03:07:41 -07:00

tracing

[CI][Tracing] Fix race condition by adding server readiness check (#34364)

2026-02-16 12:57:39 +00:00

transformers_utils

[Bugfix] Fix _CONFIG_REGISTRY types getting wrong config class when on-disk model_type differs (#39554)

2026-04-20 19:04:48 -07:00

utils_

[BugFix][CI] Fix added _has_module tests (#44248)

2026-06-01 14:23:12 -07:00

v1

[Prefix Caching] DeepSeekv4 - Support selective prefix-cache retention for sliding-window KV cache (#43447)

2026-06-04 00:48:31 -07:00

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

[ROCm][CI] Stabilize runner teardown between sampler tests (#43023)

2026-05-23 12:19:54 +08:00

test_access_log_filter.py

[Logging] add --disable-access-log-for-endpoints CLI option (#30011)

2026-01-26 21:49:03 +00:00

test_attention_backend_registry.py

…

test_config.py

[MRV2] Also enable MRV2 for Llama and Mistral dense models (#43458)

2026-06-02 11:18:46 -07:00

test_embedded_commit.py

…

test_envs.py

[Frontend][RFC] Rust front-end integration (#40848)

2026-05-21 12:24:48 +08:00

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

[Refactor] Pass full VllmConfig to Renderer (#34485)

2026-02-12 22:48:38 -08:00

test_jit_monitor.py

[Feature] Add Triton kernel JIT compilation monitor for inference (#40137)

2026-05-05 14:08:57 +04:00

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

[Model] Deprecate the score task (this will not affect users). (#37537)

2026-03-20 08:07:56 +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_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)

2026-03-15 23:35:35 +00:00

utils.py

[ROCm][CI] Extend ROCm quick reduce coverage (#40990)

2026-05-26 21:57:13 +08:00