Unverified Commit b356b499 authored by dagil-nvidia's avatar dagil-nvidia Committed by GitHub
Browse files

docs(examples): add missing --kv-transfer-config to disaggregated serving README (#6898)


Signed-off-by: default avatarDan Gil <dagil@nvidia.com>
parent 63e7b7da
...@@ -83,6 +83,7 @@ Leave this terminal running - it will show Decode Worker logs. ...@@ -83,6 +83,7 @@ Leave this terminal running - it will show Decode Worker logs.
export DYN_LOG=debug # Increase log verbosity to see disaggregation export DYN_LOG=debug # Increase log verbosity to see disaggregation
VLLM_NIXL_SIDE_CHANNEL_PORT=20097 \ VLLM_NIXL_SIDE_CHANNEL_PORT=20097 \
CUDA_VISIBLE_DEVICES=1 python -m dynamo.vllm --model Qwen/Qwen3-0.6B --disaggregation-mode prefill \ CUDA_VISIBLE_DEVICES=1 python -m dynamo.vllm --model Qwen/Qwen3-0.6B --disaggregation-mode prefill \
--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}' \
--kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20081","enable_kv_cache_events":true}' --kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20081","enable_kv_cache_events":true}'
``` ```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment