Cheng RuiandCodex 2a4e3cc3db [Bugfix][KV Offload] Ensure tracker progress for oversized offers (#54759) ...

Signed-off-by: Cheng Rui <286040359@qq.com>
Co-authored-by: Codex <noreply@openai.com>

2026-09-02 14:09:29 +03:00

..

policies

[KV Offload] Support out-of-tree secondary tier managers via module_path (#51007)

2026-08-05 20:30:53 +03:00

__init__.py

[KV Offload] Refactor CPU offloading: pluggable CachePolicy, remove Backend abstraction, restructure into cpu/ package (#37874)

2026-03-24 07:02:51 +02:00

common.py

[KV Offload] Split cpu_cache_usage_perc into write/read usage gauges (#47666)

2026-07-14 20:13:41 +03:00

gpu_worker.py

[KV offload] Order CPU->GPU loads against the compute stream (#50696)

2026-08-31 14:31:18 +03:00

manager.py

[Bugfix][KV Offload] Ensure tracker progress for oversized offers (#54759)

2026-09-02 14:09:29 +03:00

shared_offload_region.py

[Bugfix][KV Offload] Unlink /dev/shm region after all workers map it (barrier variant of #51317) (#52596)

2026-08-31 15:53:00 +03:00

spec.py

[Bugfix][KV Offload] Unlink /dev/shm region after all workers map it (barrier variant of #51317) (#52596)

2026-08-31 15:53:00 +03:00

swap_blocks_triton.py

[Perf] Triton fast path for small CPU→GPU swap_blocks_batch in the offloading connector (#42212)

2026-06-03 13:38:17 +03:00