XueLiang Yang e390742c59 Fix KV Offloading + MLA AssertionError by using num_kv_heads=1 in cpu… (#37536) ...

Signed-off-by: xueliangyang-oeuler <yxl546827391@gmail.com>
Co-authored-by: xueliangyang-oeuler <yxl546827391@gmail.com>

2026-03-19 12:05:07 +00:00

..

backends

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

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

worker

Fix KV Offloading + MLA AssertionError by using num_kv_heads=1 in cpu… (#37536)

2026-03-19 12:05:07 +00:00

__init__.py

[Docs] Enable fail_on_warning for the docs build in CI (#25580)

2025-09-24 19:30:33 +00:00

abstract.py

OffloadingConnector: Prevent redundant loads (#29087)

2026-01-21 01:15:42 +00:00

arc_manager.py

[Bugfix][CPUOffloadingManager] Prevent eviction of already-stored blocks in LRU/ARC prepare_store() (#35846)

2026-03-04 14:25:33 +02:00

backend.py

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

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

cpu.py

[kv_offload+HMA][1/N]: Support multiple KV groups in OffloadingSpec (#36610)

2026-03-13 08:04:21 +00:00

factory.py

[kv_offload+HMA][1/N]: Support multiple KV groups in OffloadingSpec (#36610)

2026-03-13 08:04:21 +00:00

lru_manager.py

[Bugfix][CPUOffloadingManager] Prevent eviction of already-stored blocks in LRU/ARC prepare_store() (#35846)

2026-03-04 14:25:33 +02:00

mediums.py

[kv_offload+HMA][2/N]: Support multiple KV groups in GPULoadStoreSpec (#36642)

2026-03-18 19:26:40 +02:00

reuse_manager.py

feat(kv-offload): Strategy A — StoreReusedOffloadingManager gates CPU stores on reuse frequency (#35342)

2026-03-10 14:43:40 +00:00

spec.py

[kv_offload+HMA][1/N]: Support multiple KV groups in OffloadingSpec (#36610)

2026-03-13 08:04:21 +00:00