3 people b3a87b2d04 [Bugfix][KVConnector] Finalize saves on steps without a forward (#57775) ...

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>

2026-09-25 00:06:36 +00:00

..

assets

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

benchmarks

[Frontend] Remove the slow tokenizer mode (#58545)

2026-09-24 08:48:28 -07:00

compilation

[Compile][CI] Honor Triton cache overrides and add AMD timeout headroom (#58474)

2026-09-24 01:27:07 -05:00

config

[ROCm][CI] skip the ROCm MRV1 default where MRV1 cannot serve the config (#58535)

2026-09-24 15:36:36 -05:00

cute_utils

[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)

2026-09-22 01:07:17 -07:00

device_allocator

[Frontend][Core] Add release_kv_cache_memory() API (#44890)

2026-09-18 07:12:12 +08:00

distributed

[Bugfix][KVConnector] Finalize saves on steps without a forward (#57775)

2026-09-25 00:06:36 +00:00

engine

[Scheduler] Tune --long-prefill-token-threshold adaptiveness (#58459)

2026-09-23 22:23:18 -04:00

entrypoints

[Frontend] Remove the slow tokenizer mode (#58545)

2026-09-24 08:48:28 -07:00

inputs

[Deprecation] Remove assistant_token_mask support (#57520)

2026-09-19 00:17:51 +08:00

ir

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

kernels

[Refactor] Move auxiliary files out of the repository root (#58572)

2026-09-24 12:38:56 -07:00

logging_utils

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

lora

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

model_executor

[Perf] Parallelize registered CUDA Triton kernel warmup at startup (#58582)

2026-09-24 19:52:00 -04:00

models

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

multimodal

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

parser

[Bugfix][Tool Parser] Migrate Granite to the streaming Parser Engine (#49648)

2026-09-23 10:37:40 +00:00

platforms

[XPU] enable XPU GRAPH by default (#51600)

2026-09-24 19:17:25 +08:00

plugins

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

profiler

[Profiler] Unify platform-aware torch profiling (#57460)

2026-09-20 19:17:23 -07:00

ray

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

reasoning

[Kimi K3 Bug] Fix kimi k3 reasoning parser (#57098)

2026-09-17 10:05:52 -07:00

renderers

[Frontend] Remove the slow tokenizer mode (#58545)

2026-09-24 08:48:28 -07:00

snapshot

[Frontend] Add reusable TP1 initialized-engine snapshots (#51360)

2026-09-21 23:18:49 +00:00

third_party

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

tilelang_utils

[Bugfix][ROCm][GLM-5.3-Flash] Apply deferred tilelang.jit already on attribute access (#57192)

2026-09-17 12:02:39 +00:00

tokenizers

[Frontend] Remove the slow tokenizer mode (#58545)

2026-09-24 08:48:28 -07:00

tool_parsers

[Bugfix][Tool Parser] Migrate Granite to the streaming Parser Engine (#49648)

2026-09-23 10:37:40 +00:00

tracing

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

transformers_utils

[BUGFIX] fix ovis2_5 multimodal tokens (#52623)

2026-09-25 07:18:54 +08:00

triton_utils

[Bugfix][CPU] Fix DeepSeek V4.1 import without Triton (#57654)

2026-09-19 05:46:13 +00:00

usage

[Bugfix] Close usage telemetry HTTP sessions (#51219)

2026-08-08 00:29:36 +00:00

utils

[Perf] DiffusionGemma: constrained reads over the request's logprob_token_ids (#58216)

2026-09-24 13:15:08 -07:00

v1

[Bugfix][KVConnector] Finalize saves on steps without a forward (#57775)

2026-09-25 00:06:36 +00:00

vllm_flash_attn

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)

2026-09-23 20:29:06 -07:00

__init__.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

_aiter_ops.py

[ROCm][Perf] Extend QK-norm/RoPE/KV-cache fusion to MRoPE (#50212)

2026-09-23 11:11:57 -05:00

_custom_ops.py

[Kernel] Remove AllSpark INT8 W8A16 GEMM backend (#58001)

2026-09-22 14:07:34 -07:00

_xpu_ops.py

[XPU] Wire up SYCL apply_rotary_emb kernel in ApplyRotaryEmb (#55721)

2026-09-22 20:43:24 -07:00

collect_env.py

[XPU] fix collecting oneccl version info (#47104)

2026-08-04 11:53:28 +00:00

connections.py

Reject oversized media before fully downloading it (#51896)

2026-08-24 01:15:09 +00:00

env_override.py

[Bugfix] Backport Inductor custom-op pattern matching fix (#58189)

2026-09-22 14:26:49 -07:00

envs.py

[Perf] Parallelize registered CUDA Triton kernel warmup at startup (#58582)

2026-09-24 19:52:00 -04:00

exceptions.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

forward_context.py

[PCP] Support prefill context parallelism with data parallelism (#57075)

2026-09-23 22:32:36 -04:00

logger.py

[CI] Support FORCE_COLOR env var; enable colors in CPU CI output (#56913)

2026-09-16 22:40:21 -04:00

logits_process.py

[Refactor] Remove dead code multiple places (#58002)

2026-09-22 16:36:03 -04:00

logprobs.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

model_inspection.py

…

outputs.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +00:00

pooling_params.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

py.typed

…

sampling_params.py

[Feat][XPU] VLLM_BATCH_INVARIANT support for Dense/MoE models (#55881)

2026-09-22 11:06:54 -04:00

scalar_type.py

[Quantization] Enable humming wNaM asymmetric quant (zero_point) with compressed-tensors (#46528)

2026-09-23 10:23:11 -04:00

scripts.py

…

sequence.py

…

tasks.py

[Frontend] Move api_server.py out openai folder (#52131)

2026-08-19 09:43:46 +00:00

version.py

…