[Feature]cpu offload connector (#1659)

Browse Source

This PR implements cpu offload connector to enable NPU kv cache offload
to host DRAM.

- vLLM version: v0.10.2
- vLLM main:
5aeb925452

Signed-off-by: lidenghui <lidenghui1110@gmail.com>
Signed-off-by: AlvisGong <gwly0401@163.com>
Signed-off-by: CalvinXKY <kyxiezju@163.com>
Co-authored-by: AlvisGong <gwly0401@163.com>

...

This commit is contained in:

lidenghui1110

2025-09-23 14:25:05 +08:00

committed by GitHub

parent 96eb1ed408

commit 0f3939e5a9

10 changed files with 990 additions and 44 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

vllm_ascend/distributed/cpu_offload_manager/__init__.py Normal file