zxr2333 ab928ed586 [v0.18.0][P/D][Feature]Layerwise connector supports Mamba prefill prefix caching (#7796) ...

### What this PR does / why we need it?
Mooncake layerwise connector supports Mamba prefix caching on prefiller
nodes.

### Does this PR introduce _any_ user-facing change?
Yes. Use `--enable-prefix-caching` and `--mamba-cache-mode align` to
enable mamba align mode prefix caching on P/D prefill nodes. This
function does not supports on decode nodes now.

### How was this patch tested?
By P/D E2E test.

---------

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

2026-03-31 09:25:22 +08:00

..

kv_p2p

[v0.18.0][P/D][Feature]Layerwise connector supports Mamba prefill prefix caching (#7796)

2026-03-31 09:25:22 +08:00

kv_pool

[Lint]Add lint hooks for clang-format, shellcheck, forbidden imports, and boolean context manager checks (#7511)

2026-03-24 20:03:01 +08:00

utils

[BugFix]Fix CI errors “ascend_transport.so: cannot open shared object file: No such file or directory” (#7242)

2026-03-14 21:23:05 +08:00

__init__.py

[feat] add LMCacheAscendConnector (#6882)

2026-03-13 17:41:35 +08:00

ascend_multi_connector.py

[P/D][KVPool]Mooncake Layerwise Connector supports kv_pool (#7032)

2026-03-09 10:49:04 +08:00