3 people 88aa0d287d [Spec decode] Support variable-length decode for Kimi-K3 adaptive ver (#52988) ...

Signed-off-by: Albert Cheng <albecheng@nvidia.com>
Signed-off-by: Albert Cheng (Engrg-Hardware 1) <albecheng@login-bia01.bia.clusters.nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

2026-09-22 20:43:32 -07:00

..

attention

[Spec decode] Support variable-length decode for Kimi-K3 adaptive ver (#52988)

2026-09-22 20:43:32 -07:00

core

[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)

2026-09-22 20:51:17 +00:00

cudagraph

[MM][V2] Enable encoder-only ViT CUDA graph capture (#56922)

2026-09-17 16:12:17 +08:00

determinism

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

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

distributed

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

e2e

[Scheduler] Soften Long Prefill Tokens Threshhold (#57951)

2026-09-21 17:19:42 -07:00

ec_connector

[EPD] Support metadata-only audio inputs (#57887)

2026-09-23 09:03:50 +08:00

engine

[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)

2026-09-22 20:51:17 +00:00

executor

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

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

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_connector

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

kv_offload

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

logits_processors

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

metrics

[Bugfix][Metrics][MFU] Size activation traffic from the model dtype (#57070)

2026-09-17 00:23:28 +00:00

sample

[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)

2026-09-22 20:51:17 +00:00

shutdown

Add pydocstyle to the ruff rules (#52136)

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

simple_kv_offload

[Bugfix][KV Offload] Skip non-prefix-cacheable groups in SimpleCPUOffload (GLM-5.3-Flash kpool tail and QSA) (#56810)

2026-09-20 10:58:55 +00:00

spec_decode

[Perf] Remove CPU-GPU sync in heterogeneous vocabulary speculative decoding (#57396)

2026-09-22 18:34:19 -04:00

streaming_input

[MM] Move supports_multimodal_inputs and cache out of registry (#57913)

2026-09-21 07:43:07 -07:00

structured_output

[Bugfix][Structured Outputs] Reject empty structural_tag at request validation (#47450)

2026-09-22 16:09:39 +03:00

tracing

[CI] Fix segfault in tracing test (#47299)

2026-07-01 14:00:37 +00:00

worker

[Spec decode] Support variable-length decode for Kimi-K3 adaptive ver (#52988)

2026-09-22 20:43:32 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

test_kv_cache_spec_registry.py

Add pydocstyle to the ruff rules (#52136)

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

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_request.py

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

test_serial_utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_tensor_ipc_queue.py

[CI] Stabilize tensor IPC multiprocessing tests (#50804)

2026-08-12 10:16:43 +08:00

utils.py

Add pydocstyle to the ruff rules (#52136)

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