scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-02 07:13:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 48
litellm/ui
History
Exact
mateo-berri e2a826c47e fix(nvidia_nim): forward logprobs and return them on chat and /v1/responses 
NVIDIA NIM serves logprobs and top_logprobs, but nvidia_nim refused both with
UnsupportedParamsError. The Responses bridge also never asked chat for logprobs
when include requested message.output_text.logprobs, leaked top_logprobs on its
own, and dropped the logprobs the model returned. It now maps include to chat
logprobs and puts the tokens on output_text and the streaming events
2026-10-30 18:33:13 -07:00
..
docker-entrypoint.d feat(helm): support a separate hostname per component in the componentized deploy (#46360) 2026-10-14 14:56:36 -07:00
litellm-dashboard fix(nvidia_nim): forward logprobs and return them on chat and /v1/responses 2026-10-30 18:33:13 -07:00
Dockerfile build(docker): refresh base images and ship only runtime files in component images (#48279) 2026-10-24 22:33:45 -07:00
nginx.conf feat(helm): support a separate hostname per component in the componentized deploy (#46360) 2026-10-14 14:56:36 -07:00