Moonchild1227 39dc4b0c2e [Feature] [KVCache] support file_store kv cache backend (#6188) ...

* fix(examples): comment out stop.sh to avoid error when script is missing

* feat: add file_store support for cache manager

* [fix] fix multi gpu transfer

* [fix] fix global kvcache transfer

* [Feature] [KVCache] support file_store kv cache backend

* chore: update FileStore according to PR comments

* fix: remove comments

* fix: add swap_cache_layout for file store

* fix: remove rank key

* fix: Switch KV cache storage to pure file mode

* Temporarily disable support for Tensor types

* fix: remove args --kvcache_file_path & add envs FILE_BACKEND_STORAGE_DIR

* fixx: Simplify cache_transfer_manager.py

* fix: fix syntax bug

* fix: Simplify file_store.py

* fix: Use the key directly as the filename

* fix: Simplify set()

* fix: Simplify cache_transfer_manager.py & file_store.py

* fix: Only support load to cpu buffer

* feat: add FileStore backend for cache transfer

* fix: guard zmq import

2026-02-03 14:37:58 +08:00

..

transfer_factory

[Feature] [KVCache] support file_store kv cache backend (#6188)

2026-02-03 14:37:58 +08:00

__init__.py

…

cache_data.py

[Feature] Support KV Cache Storage (#5571)

2025-12-25 16:30:35 +08:00

cache_messager.py

[Feature] [KVCache] support attention_store kv cache backend (#5823)

2026-01-22 21:01:23 +08:00

cache_metrics.py

[BugFix] Refine the preparation of cpu and storage cache (#5777)

2026-01-05 10:13:30 +08:00

cache_tasks.py

[Feature] [KVCache] support attention_store kv cache backend (#5823)

2026-01-22 21:01:23 +08:00

cache_transfer_manager.py

[Feature] [KVCache] support file_store kv cache backend (#6188)

2026-02-03 14:37:58 +08:00

multimodal_cache_manager.py

[Optimization] support mm prefill batch (#5313)

2025-12-11 22:21:14 +08:00

ops.py

[Metax] adapt prefix caching & cpu swap (#5844)

2025-12-31 17:02:48 +08:00

prefix_cache_manager.py

[Feature] Support report token index by attention store (#6285)

2026-02-02 10:41:11 +08:00