Originally created by @robertvazan on GitHub (Feb 3, 2024).
Is your feature request related to a problem? Please describe.
Perf info under chat response shows response speed in tokens/sec, but prompt processing speed is only shown as token count and total time.
Describe the solution you'd like
Show tokens/sec for prompt processing too.
Originally created by @robertvazan on GitHub (Feb 3, 2024).
**Is your feature request related to a problem? Please describe.**
Perf info under chat response shows response speed in tokens/sec, but prompt processing speed is only shown as token count and total time.
**Describe the solution you'd like**
Show tokens/sec for prompt processing too.
+1 Need token per second in the bottom of the webui like bottom left or right would be helpful.
Love the project.
@bolavefasfas commented on GitHub (Feb 9, 2024):
+1 Need token per second in the bottom of the webui like bottom left or right would be helpful.
Love the project.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @robertvazan on GitHub (Feb 3, 2024).
Is your feature request related to a problem? Please describe.
Perf info under chat response shows response speed in tokens/sec, but prompt processing speed is only shown as token count and total time.
Describe the solution you'd like
Show tokens/sec for prompt processing too.
@tjbck commented on GitHub (Feb 3, 2024):
Feel free to make a PR!
@bolavefasfas commented on GitHub (Feb 9, 2024):
+1 Need token per second in the bottom of the webui like bottom left or right would be helpful.
Love the project.
@tjbck commented on GitHub (Feb 18, 2024):
@dannyl1u here's another good first issue
@dannyl1u commented on GitHub (Feb 18, 2024):
Thanks, I'll work on this