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

OffloadingConnector: Add cpu_bytes_to_use configuration (#24498)

Browse Source 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
This commit is contained in:
Or Ozeri
2026-01-12 17:00:43 +02:00
committed by GitHub
parent 49e6b86c91
commit 9cddbdba6d
9 changed files with 49 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/features/disagg_prefill.md
View File

@@ -37,10 +37,10 @@ For NixlConnector, you may also specify one or multiple NIXL_Backend. Such as:
--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):
- **OffloadingConnector**: enable offloading of KV data to CPU memory, customizing the CPU block size (in tokens) and total CPU memory bytes to allocate:
```bash
--kv-transfer-config '{"kv_connector":"OffloadingConnector","kv_role":"kv_both","kv_connector_extra_config":{"block_size": 64, "num_cpu_blocks": 1000}}'
--kv-transfer-config '{"kv_connector":"OffloadingConnector","kv_role":"kv_both","kv_connector_extra_config":{"block_size": 64, "cpu_bytes_to_use": 1000000000}}'
```
## Benchmarks