biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[docs] fix nixl kv_connector_extra_config.backends key (#25565)

Browse Source 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
Signed-off-by: Peter Pan <peter.pan@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Peter Pan
2025-09-24 19:00:27 +08:00
committed by GitHub
parent 164299500b
commit b1068903fd
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/features/disagg_prefill.md
View File

@@ -34,7 +34,7 @@ Now supports 5 types of connectors:
For NixlConnector, you may also specify one or multiple NIXL_Backend. Such as:
```bash
--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_buffer_device":"cuda", "kv_connector_extra_config":{"backend":["UCX", "GDS"]}'
--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_buffer_device":"cuda", "kv_connector_extra_config":{"backends":["UCX", "GDS"]}}'
```
- **OffloadingConnector**: enable offloading of KV data to CPU memory, customizing the CPU block size (in tokens) and number of blocks to allocate (per worker):