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 9ba8a48 commit aaadcf9Copy full SHA for aaadcf9
meta-llama/Llama-3.1-8B-Instruct/performance/client.yml
@@ -1,5 +1,12 @@
1
data:
2
- prompt_tokens: 64
3
- output_tokens: 16
4
-rate-type: throughput
+ prompt_tokens: 512
+ prompt_tokens_stdev: 128
+ prompt_tokens_min: 1
5
+ prompt_tokens_max: 1024
6
+ output_tokens: 256
7
+ output_tokens_stdev: 64
8
+ output_tokens_min: 1
9
+ output_tokens_max: 1024
10
+rate-type: sweep
11
max-seconds: 400
12
+warmup-percent: 0.2
0 commit comments