docs: remove deprecated disable-log-requests flag (#22113)
Signed-off-by: Roger Wang <hey@rogerw.me>
This commit is contained in:
-2
@@ -178,7 +178,6 @@ main() {
|
||||
--max-num-seqs 256 \
|
||||
--trust-remote-code \
|
||||
--gpu-memory-utilization 0.9 \
|
||||
--disable-log-request \
|
||||
--kv-transfer-config \
|
||||
"{\"kv_connector\":\"P2pNcclConnector\",\"kv_role\":\"kv_producer\",\"kv_buffer_size\":\"1e1\",\"kv_port\":\"$kv_port\",\"kv_connector_extra_config\":{\"proxy_ip\":\"0.0.0.0\",\"proxy_port\":\"$PROXY_PORT\",\"http_port\":\"$port\",\"send_type\":\"PUT_ASYNC\",\"nccl_num_channels\":\"16\"}}" > prefill$((i+1)).log 2>&1 &
|
||||
PIDS+=($!)
|
||||
@@ -207,7 +206,6 @@ main() {
|
||||
--max-num-seqs 256 \
|
||||
--trust-remote-code \
|
||||
--gpu-memory-utilization 0.7 \
|
||||
--disable-log-request \
|
||||
--kv-transfer-config \
|
||||
"{\"kv_connector\":\"P2pNcclConnector\",\"kv_role\":\"kv_consumer\",\"kv_buffer_size\":\"8e9\",\"kv_port\":\"$kv_port\",\"kv_connector_extra_config\":{\"proxy_ip\":\"0.0.0.0\",\"proxy_port\":\"$PROXY_PORT\",\"http_port\":\"$port\",\"send_type\":\"PUT_ASYNC\",\"nccl_num_channels\":\"16\"}}" > decode$((i+1)).log 2>&1 &
|
||||
PIDS+=($!)
|
||||
|
||||
@@ -13,8 +13,7 @@ Prometheus metric logging is enabled by default in the OpenAI-compatible server.
|
||||
|
||||
```bash
|
||||
vllm serve mistralai/Mistral-7B-v0.1 \
|
||||
--max-model-len 2048 \
|
||||
--disable-log-requests
|
||||
--max-model-len 2048
|
||||
```
|
||||
|
||||
Launch Prometheus and Grafana servers with `docker compose`:
|
||||
|
||||
@@ -28,7 +28,6 @@ if [[ $1 == "prefiller" ]]; then
|
||||
CUDA_VISIBLE_DEVICES=0 \
|
||||
vllm serve $MODEL \
|
||||
--port 8100 \
|
||||
--disable-log-requests \
|
||||
--enforce-eager \
|
||||
--kv-transfer-config \
|
||||
'{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_producer","kv_connector_extra_config": {"discard_partial_chunks": false, "lmcache_rpc_port": "producer1"}}'
|
||||
@@ -46,7 +45,6 @@ elif [[ $1 == "decoder" ]]; then
|
||||
CUDA_VISIBLE_DEVICES=1 \
|
||||
vllm serve $MODEL \
|
||||
--port 8200 \
|
||||
--disable-log-requests \
|
||||
--enforce-eager \
|
||||
--kv-transfer-config \
|
||||
'{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_consumer","kv_connector_extra_config": {"discard_partial_chunks": false, "lmcache_rpc_port": "consumer1"}}'
|
||||
|
||||
Reference in New Issue
Block a user