[KV offload][5/N] Add CPUOffloadingSpec (#24251)
Signed-off-by: Or Ozeri <oro@il.ibm.com> Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@ -31,6 +31,12 @@ Now supports 5 types of connectors:
|
||||
--kv-transfer-config '{"kv_connector":"MultiConnector","kv_role":"kv_both","kv_connector_extra_config":{"connectors":[{"kv_connector":"NixlConnector","kv_role":"kv_both"},{"kv_connector":"SharedStorageConnector","kv_role":"kv_both","kv_connector_extra_config":{"shared_storage_path":"local_storage"}}]}}'
|
||||
```
|
||||
|
||||
- **OffloadingConnector**: enable offloading of KV data to CPU memory, customizing the CPU block size (in tokens) and number of blocks to allocate (per worker):
|
||||
|
||||
```bash
|
||||
--kv-transfer-config '{"kv_connector":"OffloadingConnector","kv_role":"kv_both","kv_connector_extra_config":{"block_size": 64, "num_cpu_blocks": 1000}}'
|
||||
```
|
||||
|
||||
## Benchmarks
|
||||
|
||||
Please refer to <gh-file:benchmarks/disagg_benchmarks> for disaggregated prefilling benchmarks.
|
||||
|
||||
Reference in New Issue
Block a user