Files
anything-llm/server
Marcello Fitton 1ccf468158 fix: correct TPS calculation for Generic OpenAI provider with llama.cpp (#4981)
* add check for timings field on final chunk to override usage data

* refactor: extract llama.cpp timings into reusable private method

Move timings extraction into #extractTimings so it can be shared
by both streaming (handleStream) and non-streaming (getChatCompletion)
code paths.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* lint and cleanup

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2026-02-12 14:40:35 -08:00
..
2026-02-02 10:56:58 -08:00
2026-02-11 08:53:44 -08:00
2024-01-08 15:31:06 -08:00
2026-02-02 10:56:58 -08:00
2026-02-02 10:56:58 -08:00
2024-01-08 15:31:06 -08:00
2023-08-23 19:15:07 -07:00