New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Use min-decode-steps = 256 by default for server and benchmark #47

Merged

masahi merged 1 commit into octoml:batch-serving from masahi:engine-tweak

Nov 2, 2023

Member

masahi commented Nov 2, 2023

13B fp16

Before: Throughput: 4.64 requests/s, 2218.75 tokens/s 
After: Throughput: 5.12 requests/s, 2449.24 tokens/s
vLLM: Throughput: 5.20 requests/s, 2488.75 tokens/s


          Use min-decode-steps = 256 by default for server and benchmark

9235d42

masahi merged commit 3554164 into octoml:batch-serving

5 checks passed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet