Yan Ma 58cfe0dc44 Fix phi4-mm and remove cuda binding (#35964) ...

Signed-off-by: Yan Ma <yan.ma@intel.com>

2026-03-05 01:08:05 +08:00

..

assets

[Model] Nemotron Parse 1.1 Support (#30864)

2026-01-05 13:00:14 -08:00

benchmarks

[Benchmark] Avoid unnecessary video download in MMVU (#35618)

2026-02-28 09:07:02 -08:00

compilation

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

config

[Misc] Add --attention-backend auto option (#35738)

2026-03-04 15:12:27 +00:00

device_allocator

[CI] Fix mypy for vllm/device allocator (#35518)

2026-03-02 15:53:18 +00:00

distributed

[BugFix] Fix implicit and incorrect assumption on ECConnector is_producer (#34783)

2026-03-04 15:01:30 +01:00

engine

[Misc] Add --attention-backend auto option (#35738)

2026-03-04 15:12:27 +00:00

entrypoints

[Feature] Add basic metrics for /realtime endpoint (#35500)

2026-03-04 19:56:32 +08:00

grpc

[grpc] Support gRPC server entrypoint (#30190)

2026-01-07 23:24:46 -08:00

inputs

[Renderer] Move MM Hash parsing into Renderer (#34711)

2026-02-17 19:18:55 -08:00

kernels

[Kernel] [Helion] [7/N] Use HOP to represent Helion Kernel call to enable fx tracing and pattern matching (#34390)

2026-02-27 09:21:35 -08:00

logging_utils

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

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

lora

[MoE Refactor] Create MK for TRTLLM Kernels (#32564)

2026-03-03 10:39:50 -08:00

model_executor

Fix phi4-mm and remove cuda binding (#35964)

2026-03-05 01:08:05 +08:00

multimodal

Support Audio Extraction from MP4 Video for Nemotron Nano VL (#35539)

2026-03-03 23:20:33 -08:00

parser

[2/N] move responses/serving _make_response_output_items logic to parser (#33281)

2026-02-05 13:46:15 +08:00

platforms

[ROCm][Bugfix]: Disable AITER Triton ROPE by default (#35601)

2026-03-03 13:43:56 -06:00

plugins

add io_process_plugin for sparse embedding (#34214)

2026-02-28 09:16:37 +00:00

profiler

[Misc] Fix mypy errors in vllm/profiler and remove from exclude list (#34959)

2026-02-20 19:56:33 -08:00

ray

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)

2026-02-17 01:08:42 -08:00

reasoning

[Bugfix] Handle case when kimi ends reasoning with a tool call (#33646)

2026-02-27 14:58:28 +00:00

renderers

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

third_party

[FlashMLA] Update FlashMLA to expose new arguments (#32810)

2026-01-21 22:02:39 -07:00

tokenizers

[Feature] Lazy import for the "mistral" tokenizer module. (#34651)

2026-02-23 00:43:01 -08:00

tool_parsers

[MISC] fixed tool_parser mypy errors (#35640)

2026-03-04 12:23:12 +00:00

tracing

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

transformers_utils

[Bugfix] Make kaldi_native_fbank optional (#35996)

2026-03-04 06:47:32 -08:00

triton_utils

Add TMA support to fused_moe_lora kernel (#32195)

2026-03-01 10:55:25 +08:00

usage

[Deprecation] Remove deprecated environment variables (#32812)

2026-01-22 02:25:16 +00:00

utils

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

v1

[Core] Add All-to-All communication backend for DCP (#34883)

2026-03-04 10:01:57 -05:00

vllm_flash_attn

[Attention] FA4 integration (#32974)

2026-03-01 23:44:57 +00:00

__init__.py

Remove bc-lint (#35274)

2026-02-26 03:01:01 -08:00

_aiter_ops.py

[ROCm][Quantization] Add Composable Kernel (CK) backend support for M… (#34301)

2026-02-28 03:37:01 +00:00

_custom_ops.py

[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448)

2026-03-01 23:31:19 -08:00

_oink_ops.py

[Perf] Add opt-in SM100 Oink RMSNorm custom-op path (#31828)

2026-02-24 23:01:53 -08:00

_xpu_ops.py

[XPU]Fix for Qwen-OMNI crash (#35249)

2026-02-25 07:31:07 -08:00

beam_search.py

[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)

2026-02-17 05:29:01 -08:00

collect_env.py

[Refactor] Remove unused dead code (#33718)

2026-02-03 21:25:11 -08:00

connections.py

[Misc] Replace urllib's urlparse with urllib3's parse_url (#32746)

2026-01-22 16:37:15 +08:00

env_override.py

[torch.compile] Undo the fast_moe_cold_start hack in torch>=2.11 (#35475)

2026-03-01 21:44:22 +00:00

envs.py

[Core] Remove busy loop from idle buffer readers (#28053)

2026-03-04 07:44:20 +00:00

exceptions.py

[OpenAI] Extend VLLMValidationError to additional validation parameters (#31870)

2026-01-07 14:45:49 +00:00

forward_context.py

[DP] Only use DP padding when cudagraphs are actually used (#34102)

2026-02-27 15:14:31 -05:00

logger.py

[CI] Enable mypy coverage for individual excluded files (#34292)

2026-02-16 07:34:29 -08:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

logprobs.py

Make mypy opt-out instead of opt-in (#33205)

2026-01-29 09:12:26 +00:00

model_inspection.py

[UX] Add vLLM model inspection view (#29450)

2026-01-09 10:12:35 -07:00

outputs.py

[V0 Deprecation] Remove unused MM placeholders in request output (#34944)

2026-02-20 06:19:23 -08:00

pooling_params.py

[Deprecation] Deprecate code in 0.17 as scheduled (#35441)

2026-02-28 17:32:37 +00:00

py.typed

…

sampling_params.py

[Core] Add optional flags to check for repetitive token patterns in engine output (#35451)

2026-03-03 12:23:25 +08:00

scalar_type.py

…

scripts.py

…

sequence.py

[Chore] Remove more V0 dead code from sequence.py (#31783)

2026-01-06 10:25:14 +00:00

tasks.py

[Realtime API] Adds minimal realtime API based on websockets (#33187)

2026-01-30 18:41:29 +08:00

version.py

…