andreas/llama-swap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
255 Commits 1 Branch 0 Tags
01d4838fb3aa3db52087135ffbd87c598874a7d5
Commit Graph

3 Commits

Author SHA1 Message Date
Benson Wong
01d4838fb3 Fix token metrics parsing (#199) 
Fix #198

- use llama-server's `timings` info if available in response body
- send "-1" for token/sec when not able to accurately calculate
  performance
- optimize streaming body search for metrics information
 2025-07-22 23:10:14 -07:00
Benson Wong
9a54273d15 Update UI with new Activity event stream from #195 
- use new metrics data instead of log parsing
- auto-start events connection to server, improves responsiveness
- remove unnecessary libraries and code
 2025-07-21 22:42:30 -07:00
g2mt
87dce5f8f6 Add metrics logging for chat completion requests (#195) 
- Add token and performance metrics  for v1/chat/completions 
- Add Activity Page in UI
- Add /api/metrics endpoint

Contributed by @g2mt
 2025-07-21 22:19:55 -07:00