karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[CI/Docs] Remove stale disagg prefill links (#44918)

Browse Source 
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
This commit is contained in:
Mohammad Miadh Angkad
2026-06-09 03:05:53 -07:00
committed by GitHub
parent 70db1488c5
commit fff9210b2a
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/features/disagg_prefill.md
-4
View File
@@ -47,10 +47,6 @@ Now supports 9 types of connectors:
--kv-transfer-config '{"kv_connector":"FlexKVConnectorV1","kv_role":"kv_both"}'
```
## Benchmarks
Please refer to [benchmarks/disagg_benchmarks](../../benchmarks/disagg_benchmarks) for disaggregated prefilling benchmarks.
## Development
We implement disaggregated prefilling by running 2 vLLM instances. One for prefill (we call it prefill instance) and one for decode (we call it decode instance), and then use a connector to transfer the prefill KV caches and results from prefill instance to decode instance.