We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent aff567f commit 1bb8483Copy full SHA for 1bb8483
meta-llama/Llama-3.1-8B-Instruct/performance/client.yml
@@ -1,8 +1,6 @@
1
-target: "http://localhost:8000/v1"
2
-model: "meta-llama/Llama-3.1-8B-Instruct"
3
data:
4
prompt_tokens: 64
5
- output_tokens: 16
+ generated_tokens: 16
+data-type: emulated
6
rate-type: throughput
7
max-seconds: 400
8
-output_path: ""
meta-llama/Llama-3.1-8B-Instruct/performance/server.yml
@@ -1,6 +1,5 @@
# server configs for https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
# config.yaml
-model: meta-llama/Llama-3.1-8B-Instruct
uvicorn-log-level: "debug"
trust-remote-code: true
enable-chunked-prefill: true
0 commit comments