Jee Jee Li 715681c127 [LoRA] Support dual CUDA streams-Linear Layer (#35721) ...

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

2026-04-13 10:57:07 +08:00

..

basic_correctness

…

benchmarks

…

compile

[compile] Bug fix for _decompose_size_nodes (#38360)

2026-04-12 20:20:24 +00:00

config

…

cuda

…

detokenizer

…

distributed

[HMA] [KVEvent] Enable GPU-side KV events for HMA (#37688)

2026-04-12 10:01:02 +03:00

engine

[Feature] NUMA binding support for GPU workers (#38635)

2026-04-08 09:55:24 -07:00

entrypoints

[Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214)

2026-04-10 01:36:26 +00:00

evals

[Kernels][MoE] Fix legacy_routing to use bitmatrix-based routing path (#38504)

2026-04-07 10:57:09 +08:00

ir

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00

kernels

[Bugfix] [Tests] Enforce out tensor device in kernel/moe/test_cutedsl_moe.py (#39644)

2026-04-12 17:08:08 -07:00

lora

[LoRA] Support dual CUDA streams-Linear Layer (#35721)

2026-04-13 10:57:07 +08:00

model_executor

fix(moe): fix RoutedExpertsCapturer assertion failure with DP>1 and MK path (#37879)

2026-04-12 10:28:17 -04:00

models

[New Model]: jinaai/jina-reranker-v3 (#38800)

2026-04-10 15:20:40 +00:00

multimodal

(security) Enforce frame limit in VideoMediaIO (#38636)

2026-04-01 10:23:45 +00:00

plugins

…

plugins_tests

…

prompts

…

quantization

[Quant] add CompressedTensorsW8A8Mxfp8 for linear and MoE layers (#38815)

2026-04-11 17:21:36 -06:00

reasoning

[Tool] adjust_request to reasoning parser, and Gemma4 fixes (#39027)

2026-04-08 19:04:04 +00:00

renderers

[Tool] adjust_request to reasoning parser, and Gemma4 fixes (#39027)

2026-04-08 19:04:04 +00:00

rocm/aiter

…

samplers

…

standalone_tests

Add structure to requirements/ directory (#39024)

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

system_messages

…

tokenizers_

[Mistral Grammar] Support Grammar Factory (#38150)

2026-04-06 10:28:51 -04:00

tool_parsers

[Tool] adjust_request to reasoning parser, and Gemma4 fixes (#39027)

2026-04-08 19:04:04 +00:00

tool_use

…

tools

…

tracing

…

transformers_utils

[GGUF] Support non-standard quant types with prefix (e.g. UD-IQ1_S) (#39471)

2026-04-10 07:22:53 +00:00

utils_

[Feature] NUMA binding support for GPU workers (#38635)

2026-04-08 09:55:24 -07:00

v1

[KVConnector][NIXL] Organize NIXL connector into its own directory (#39354)

2026-04-12 13:10:50 +00:00

vllm_test_utils

…

weight_loading

…

__init__.py

…

ci_envs.py

…

conftest.py

[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

2026-04-09 08:50:39 +08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_config.py

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00

test_embedded_commit.py

…

test_envs.py

…

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

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

…

test_ray_env_utils.py

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

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

test_ray_env.py

…

test_regression.py

…

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

…

utils.py

[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

2026-04-09 08:50:39 +08:00