3 people f9d666f917 [KV Offload] Forward ownership in KV cache events (#52067) ...

Signed-off-by: Moein Khazraee <moein@nvidia.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

2026-08-31 10:28:41 +03:00

..

attention

[Bugfix][MLA] Fix BLHNC addressing for FlashInfer sparse MLA (#54465)

2026-08-31 01:13:42 +00:00

core

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

cudagraph

[Bugfix][Spec Decode] Capture the widest uniform decode batch by default (#50488)

2026-08-28 22:38:13 -07:00

determinism

[Test][VLM] Add batch-invariance tests for Qwen3-VL (#53531)

2026-08-30 09:49:41 -04:00

distributed

[Bugfix][DP] Synchronize the device on pause completion (#52914)

2026-08-26 09:50:33 -07:00

e2e

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

ec_connector

[EC Connector] EC Offloading Connector use events instead of StepTracker (#49994)

2026-08-27 03:41:46 +00:00

engine

[Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162)

2026-08-28 22:09:08 -07:00

executor

[Bugfix] Release worker RPC payload before next dequeue (#51979)

2026-08-24 07:27:36 -07:00

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

[KV Offload] Forward ownership in KV cache events (#52067)

2026-08-31 10:28:41 +03:00

kv_offload

Count store offers, not lookups, for CPU offload store_threshold (#52227)

2026-08-27 20:21:06 -07:00

logits_processors

[Bugfix] Preserve non-logitproc entry points in tests (#51097)

2026-08-10 18:14:53 -04:00

metrics

[Refactor] Move iteration logging to the frontend (#46647)

2026-07-15 17:59:05 -07:00

sample

[Model Runner V2] Reserve CUDA graph memory (#53306)

2026-08-23 23:11:19 -07:00

shutdown

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

simple_kv_offload

[Core][KV Connector] Start async KV loads after the forward launch when no sync loads are scheduled (#53333)

2026-08-28 21:58:00 +00:00

spec_decode

[Bugfix][Model Runner V2][Spec Decode] Decouple the draft's gumbel noise stream from the target's (#54282)

2026-08-29 09:58:29 -07:00

streaming_input

[Spec Decode] DSpark confidence-scheduled verification (#47808)

2026-08-12 12:27:48 -07:00

structured_output

[Bugfix] Support MistralCommonBackend tokenizers in structured output (#52720)

2026-08-20 19:08:50 +01:00

tracing

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

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

worker

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_kv_cache_spec_registry.py

[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)

2026-08-14 09:47:55 -04:00

test_oracle.py

[Docs] Clean up speculators docs (#34065)

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

test_outputs.py

[Feature][DSpark]: Logprobs adaptive verification (#52242)

2026-08-25 10:22:33 -04:00

test_request.py

feat(frontend): session id plumbing into requests (#48048)

2026-08-03 22:18:58 +00:00

test_serial_utils.py

[Bugfix] Don't reuse engine core payload buffer while zmq is sending it (#50053)

2026-07-28 16:09:28 +00:00

test_tensor_ipc_queue.py

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

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

utils.py

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

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