4 people 676650397f [Feature][PCP] Support decode-only FULL CUDA graphs (#53867) ...

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: QiuChunshuo <chunshuoq@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-09-15 16:27:46 +08:00

..

attention

[Bugfix][SparseMLA] Fix piecewise cudagraph capture crash in index group (#56825)

2026-09-15 06:51:35 +00:00

core

[Bugfix][Kimi-K3] Keep transient checkpoints out of prefix-cache eviction (#56794)

2026-09-15 14:18:24 +08:00

engine

[Bugfix] Validate routed-expert prompt offsets before engine submission (#56844)

2026-09-15 09:17:41 +08:00

executor

[Refactor] Remove utils dead code (#53941)

2026-09-08 11:22:09 -04:00

fault_tolerance

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

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

hisparse

[Bugfix][SparseMLA] Fix piecewise cudagraph capture crash in index group (#56825)

2026-09-15 06:51:35 +00:00

kv_offload

[KV Offload] Add KVCR secondary-tier adapter (#53624)

2026-09-15 09:55:04 +03:00

metrics

[Bugfix] Make KV cache and MFU log lines backend-neutral (#55650)

2026-09-14 18:00:20 +00:00

pool

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

sample

[6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)

2026-09-12 17:24:24 -07:00

simple_kv_offload

[Bugfix][KV Offload] Submit CPU stores on no-forward steps (#56621)

2026-09-13 05:56:14 +00:00

spec_decode

[Doc][Metrics] Fix spec-decode PromQL examples to use the exposed names (#55016)

2026-09-14 21:15:28 +00:00

structured_output

[feature] [xgrammar] support patternProperties/propertyNames/unevaluatedProperties kw for object types (#42904)

2026-09-15 12:58:52 +08:00

watermarking

[watermarking] Dual-key gumbel-max watermarking for speculative decoding support (#56122)

2026-09-12 18:42:01 +00:00

worker

[Feature][PCP] Support decode-only FULL CUDA graphs (#53867)

2026-09-15 16:27:46 +08:00

__init__.py

…

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

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

kv_cache_interface.py

[Bugfix][KV Connector] MooncakeStore: exclude non-prefix-cacheable (QSA ring) groups; fix align-mode check (#55027)

2026-09-13 19:18:16 -07:00

kv_cache_layout.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

kv_cache_spec_registry.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

outputs.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

request.py

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

serial_utils.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

utils.py

[Bugfix][Frontend] Keep credentials out of the Rust frontend launch log (#53738)

2026-08-25 16:32:12 +00:00