Michael GoinandOpenAI Codex e18f0037a5 [Bugfix][KV cache] Support sparse-MLA targets with SWA drafts (#48776) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-07-23 11:30:50 -07:00

..

attention

[Bugfix][Attention] Ignore empty MLA context chunks during merge (#49294)

2026-07-22 02:23:48 +00:00

core

[Bugfix][KV cache] Support sparse-MLA targets with SWA drafts (#48776)

2026-07-23 11:30:50 -07:00

engine

[Bugfix][Spec Decode] Select earliest-completing stop string in check_stop_strings (#49391)

2026-07-23 18:14:06 +08:00

executor

[CI/Build][The Rock][BugFix] Use fork method in test_multiproc_executor_multi_node for py 3.14 compat and fix test_multiproc_executor_shutdown_cleanup (#48655)

2026-07-21 15:40:29 -05:00

kv_offload

[KV Offload] Support self-describing KV events with TieringOffloadingSpec (#48679)

2026-07-20 16:41:58 +03:00

metrics

[Front-end] [Messages] Populate num_cache_creation_tokens (#48535)

2026-07-18 13:04:35 -04:00

pool

[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014)

2026-07-08 18:30:11 +00:00

sample

[MRV2][Spec Decode] Avoid rejection sampler OOM by chunking (#48630)

2026-07-23 18:13:13 +08:00

simple_kv_offload

[Bugfix][KV Offload] Propagate EAGLE mode to SimpleCPU coordinator (#49071)

2026-07-20 06:39:11 +00:00

spec_decode

[Bugfix][Spec Decode] Restrict embedding-width share guard to EAGLE drafts (#47953)

2026-07-21 10:53:37 -07:00

structured_output

[Bugfix] Restore structured output logger initialization (#49626)

2026-07-23 11:26:03 -07:00

worker

Revert "[MRV2] Always build attn metadata at capture time" (#49364) (#49451)

2026-07-23 09:51:33 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

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

kv_cache_interface.py

[Bugfix] Zero new KV blocks for quantized + sliding-window hybrid caches (#47574)

2026-07-20 13:18:17 +00:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

2026-06-03 09:05:16 -07:00

outputs.py

[MRV2][Spec Decode] Avoid rejection sampler OOM by chunking (#48630)

2026-07-23 18:13:13 +08:00

request.py

[Core] Preserve Marconi caching with selective hybrid cache retention (#47782)

2026-07-13 21:24:20 +01:00

serial_utils.py

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

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

utils.py

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

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