vllm/vllm at 78434b923c80e435bcae9ad846471a48d8e3bb4e - vllm

assets

[Frontend] Remove librosa from audio dependency (#37058 )

2026-03-21 11:36:15 +08:00

benchmarks

[Misc] Reorganize inputs (#35182 )

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

compilation

[vLLM IR] rework gemma_rms_norm (#39014 )

2026-04-07 01:37:00 -07:00

config

[Attention][V0 Deprecation] Deprecate accept output buffer (#39125 )

2026-04-07 17:14:58 -04:00

device_allocator

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

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

distributed

[release 2.11] Update to torch 2.11 (#34644 )

2026-04-07 18:55:48 -07:00

engine

[Frontend] new online quantization frontend (#38138 )

2026-04-03 11:58:39 -04:00

entrypoints

[Parser] Migrate response api streaming to unified parser (#38755 )

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

inputs

[Misc] Reorganize inputs (#35182 )

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

ir

[vLLM IR] rework gemma_rms_norm (#39014 )

2026-04-07 01:37:00 -07:00

kernels

[vLLM IR] rework gemma_rms_norm (#39014 )

2026-04-07 01:37:00 -07:00

logging_utils

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

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

lora

Revert "[Kernel] Add gpt-oss Router GEMM kernel (#37205 )" (#38778 )

2026-04-01 22:02:32 -07:00

model_executor

[CI][AMD][BugFix][Kernel] Cast induction variable to int64 on MI350 for chunk_gated_delta_rule_fwd_kernel_h_blockdim64 to avoid illegal memory access (#39087 )

2026-04-08 16:57:18 +08:00

multimodal

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

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

parser

[Parser] Migrate response api streaming to unified parser (#38755 )

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

platforms

docs: clarify SMT and OMP acronyms in CpuPlatform (#39085 )

2026-04-07 17:42:07 -07:00

plugins

[Misc] Reorganize inputs (#35182 )

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

profiler

Add PyTorch profiler schedule support with warmup/active iterations (#35240 )

2026-03-04 12:53:38 -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

feat(models): implement Google Gemma 4 architecture support (MoE, Multimodal, Reasoning, Tool-Use) (#38826 )

2026-04-02 11:13:28 -07:00

renderers

[Bugfix] Use dedicated MM processor cache in /tokenize to prevent sender-cache pollution (#38545 )

2026-04-01 21:14:49 -07:00

third_party

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

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

tokenizers

[Mistral Grammar] Support Grammar Factory (#38150 )

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

tool_parsers

[Bugfix][Frontend] Fix Gemma4 streaming HTML duplication after tool calls (#38909 )

2026-04-08 11:03:54 +08:00

tracing

[Feature] OTEL tracing during loading (#31162 )

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

transformers_utils

Fix Mistral yarn warning in Transformers v5 (#37292 )

2026-04-07 13:23:33 +00:00

triton_utils

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230 )

2026-03-11 19:19:15 +08:00

usage

replace cuda_device_count_stateless() to current_platform.device_count() (#37841 )

2026-03-31 22:32:54 +08:00

utils

[release 2.11] Update to torch 2.11 (#34644 )

2026-04-07 18:55:48 -07:00

v1

[Model Runner V2] Fuse probabilistic rejection sample kernels (#38496 )

2026-04-07 17:37:37 -07:00

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][perf] Shuffle KV cache to use paged_attention_common (#32914 )

2026-04-01 03:30:19 +00:00

_custom_ops.py

[Perf] Batch KV cache swap copies via cuMemcpyBatchAsync (#38460 )

2026-04-03 03:13:23 +00:00

_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] add xpu backend implementation of mxfp8 quant (#38682 )

2026-04-08 08:30:35 +08:00

beam_search.py

[Misc] Reorganize inputs (#35182 )

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

collect_env.py

[Refactor] Remove unused dead code (#33718 )

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

connections.py

[CI] Add retry with 4x backoff to HTTP fetches for transient failures (#37218 )

2026-03-19 19:00:20 +00:00

env_override.py

only patch runtime_env for torch >= 2.10 (#38763 )

2026-04-07 09:29:23 +00:00

envs.py

[NVFP4] Support NVFP4 dense models from modelopt and compressed-tensors on AMD Instinct MI300, MI355X and Hopper through emulation (#35733 )

2026-04-06 16:18:27 -06:00

exceptions.py

[openapi server] log exception in exception handler(2/N) (#36201 )

2026-03-10 20:16:30 -07:00

forward_context.py

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

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

logger.py

[Log] Log once in local node by default (#37568 )

2026-03-19 12:04:59 -07:00

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

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

2026-03-20 08:07:56 +00:00

py.typed

…

sampling_params.py

[Mistral Grammar] Support Grammar Factory (#38150 )

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

scalar_type.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

scripts.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

sequence.py

[Model Runner V2][Minor] Simplify PP logic (#38031 )

2026-03-24 13:57:17 -07:00

tasks.py

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

2026-03-20 08:07:56 +00:00

version.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00