mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-22 16:07:51 +08:00
[Metax][Test] enable paddleocr using cudagraph (#6820)
This commit is contained in:
@@ -36,7 +36,7 @@ SERVER_CMD="python -m fastdeploy.entrypoints.openai.api_server \
|
||||
--max-num-batched-tokens 16384 \
|
||||
--gpu-memory-utilization 0.7 \
|
||||
--max-num-seqs 256 \
|
||||
--graph-optimization-config '{\"use_cudagraph\": false}' \
|
||||
--graph-optimization-config '{\"use_cudagraph\": true}' \
|
||||
--workers 4 \
|
||||
--max-concurrency 8192 \
|
||||
--port 8118 \
|
||||
|
||||
Reference in New Issue
Block a user