v143

Changelog

• 8c693e7 Add endpoint aliases for reranking models (#201)

v142

Changelog

• 8f2af26 fix stats on model page

v141

This release changes the way tokens/second are calculated on the activities page. The previous method was inaccurate because it divided the number of tokens generated by the total request time. The total request time also included prompt processing so the number was too misleading to be useful.

This release changes the logic to:

• use llama-server's timings record if it exists for tokens/second
• send a -1 when timings is not available. The UI will render this as "unknown".

Supporting timing information for other inference engines will be future PRs.

Token/Second and duration now match llama-server's output precisely:

Changelog

• 01d4838 Fix token metrics parsing (#199)
• accd652 add contributors to README [skip ci]
• 7472a25 Update README.md [skip ci]

v140

v140 includes a new feature to track chat completion activity in llama-swap.

Thanks to @g2mt for the contribution!

Changelog

• cce0bc6 add guard to ensure ls-real-model-name is set in context
• 36e2512 UI tidy [skip ci]
• 9a54273 Update UI with new Activity event stream from #195
• 87dce5f Add metrics logging for chat completion requests (#195)
• 307e619 remove old eventsources from UI

v139

Changelog

• 6299c1b Fix High CPU (#189)

v138

Changelog

• a906cd4 Strip comments before macro expansion in config (#193)

v137

Changelog

• 78b2bc3 add toggle to hide/show unlisted models (#187)

v136

Changelog

• 6a058e4 Change fsnotify to watch config directory instead of file

v135

Changelog

• 1921e57 Add Event Bus (#184)

v134

Changelog

• c867a6c Add name and description to v1/models list (#179)
• 3bd1b23 fix config hot-reload on k8s (#181)