maobaolongandLi, Jiang <jiang1.li@intel.com> 13726c80fe [CPU] Add MLA backend so DeepSeek-V2/V3 can run on CPU (#49453) ...

Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>

2026-08-06 16:51:41 +08:00

..

attention

[CPU] Add MLA backend so DeepSeek-V2/V3 can run on CPU (#49453)

2026-08-06 16:51:41 +08:00

core

[BugFix][KV Cache] Fix hybrid prefix caching with hidden-state extraction (#51108)

2026-08-06 06:42:37 +00:00

engine

[BugFix] Dense multinode DP rescope with regression test (#49212)

2026-08-05 18:12:03 -07:00

executor

[Core] Explicitly manage torch CPU threads in workers (#49919)

2026-08-04 10:06:38 -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_offload

[Bugfix] Fail fast with a clear error when CPU offload region exceeds available space (#50358)

2026-08-05 20:59:55 +03:00

metrics

[R3] Unify routed expert shape configuration (#50940)

2026-08-04 20:20:41 -07:00

pool

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

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

sample

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

simple_kv_offload

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

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

spec_decode

[Bugfix][Model Runner V2] Restore multimodal draft capability detection (#50417)

2026-08-03 14:18:14 -07:00

structured_output

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

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

worker

[Model Runner V2] Cache draft logits in model's LM head dtype (#50910)

2026-08-05 19:12:46 -07:00

__init__.py

…

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

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

kv_cache_interface.py

[Bugfix] Shard UniformTypeKVCacheSpecs block table width under DCP (#50823)

2026-08-03 17:34:29 +00:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

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

outputs.py

[Bugfix][EC Connector] Don't stop an encoder-instance request before its images are encoded (#50275)

2026-08-05 05:53:58 +00:00

request.py

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

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

serial_utils.py

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

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

utils.py

[chore] log process manager shutdown with more details (#49437)

2026-07-31 11:55:09 -07:00