3 people d467a2a7f2 [Bugfix] Defer block freeing until in-flight steps finish under async scheduling + PD KV consumer (#45357) ...

Signed-off-by: llx-08 <2596671364@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-06-15 21:36:09 +00:00

..

assets

Add vLLM library info to Hugging Face Hub requests (#43857)

2026-05-29 14:04:58 +00:00

benchmarks

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

compilation

[XPU] Enable sequence parallel support for XPU (#38608)

2026-06-14 19:26:46 -07:00

config

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

cute_utils

…

device_allocator

[XPU][Feature] transparent sleep mode support for XPU platform (#37149)

2026-06-07 10:45:31 +08:00

distributed

[KV Connector]: Support KV push from Prefill to Decode node using Nixl KV Connector (#35264)

2026-06-12 10:38:41 +00:00

engine

[Migration] Migrate GGUF quantization support to plugin (#39612)

2026-06-12 12:02:21 -07:00

entrypoints

Fix parallel_tool_calls: null treated as false instead of default true (#44955)

2026-06-15 21:14:10 +00:00

inputs

…

ir

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

kernels

[Kernel][Helion][1/N] Add Helion kernel for dynamic_per_token_scaled_fp8_quant (#33790)

2026-06-12 12:50:06 -04:00

logging_utils

…

lora

[Bugfix][MoE] Fix fused MoE expert mapping helper call sites (#44897)

2026-06-08 13:35:04 -07:00

model_executor

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

models

[Perf] Optimize DSv4 prefill chunk planning, 4.0% E2E Throughput Improvement (#45061)

2026-06-15 19:50:21 +00:00

multimodal

Fix misleading error for audio duration limit rejection (#45113)

2026-06-12 09:58:08 +00:00

parser

[Frontend] Replace legacy Gemma4 parsers with engine-based implementation (#45588)

2026-06-15 21:34:07 +00:00

platforms

[XPU] Enable sequence parallel support for XPU (#38608)

2026-06-14 19:26:46 -07:00

plugins

Add vLLM library info to Hugging Face Hub requests (#43857)

2026-05-29 14:04:58 +00:00

profiler

…

ray

…

reasoning

[Frontend] Replace legacy Gemma4 parsers with engine-based implementation (#45588)

2026-06-15 21:34:07 +00:00

renderers

Deprecated 1st generation Qwen and QwenVL models (#45131)

2026-06-10 14:55:33 +00:00

third_party

…

tokenizers

[Bugfix] Return the tokenizer from maybe_make_thread_pool so it survives pickling (#45460)

2026-06-13 06:01:35 +00:00

tool_parsers

[Frontend] Replace legacy Gemma4 parsers with engine-based implementation (#45588)

2026-06-15 21:34:07 +00:00

tracing

…

transformers_utils

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

triton_utils

…

usage

…

utils

[Bugfix][CPU] Honor cgroup memory limit when computing KV cache size (#45086)

2026-06-14 19:26:50 -07:00

v1

[Bugfix] Defer block freeing until in-flight steps finish under async scheduling + PD KV consumer (#45357)

2026-06-15 21:36:09 +00:00

vllm_flash_attn

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

__init__.py

…

_aiter_ops.py

[ROCm][gpt-oss] Pass GateMode.INTERLEAVE for MXFP4 W4A16 fused MoE (#44893)

2026-06-12 01:02:04 -05:00

_custom_ops.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

_xpu_ops.py

[BUGFIX][XPU] Update fa interface for compatibility (#45394)

2026-06-12 11:45:01 +00:00

collect_env.py

…

connections.py

…

env_override.py

[Inductor] Fast-path Inductor fallback for vllm::*/vllm_aiter::* custom ops (#42129)

2026-06-04 00:03:52 -05:00

envs.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

exceptions.py

…

forward_context.py

…

logger.py

…

logits_process.py

…

logprobs.py

…

model_inspection.py

…

outputs.py

…

pooling_params.py

…

py.typed

…

sampling_params.py

[Bugfix] Reject out-of-range temperature values in SamplingParams (#44965)

2026-06-14 23:12:44 -07:00

scalar_type.py

…

scripts.py

…

sequence.py

…

tasks.py

…

version.py

…