]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e457fb3)
server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seco...
authorPierrick Hymbert <redacted>
Fri, 8 Mar 2024 11:25:04 +0000 (12:25 +0100)
committerGitHub <redacted>
Fri, 8 Mar 2024 11:25:04 +0000 (12:25 +0100)
commit76e868821a94072fbc87cb1fcca291694319eae8
treec25aeb945cd47b39875a24df0bc42abbb60196a6tree
parente457fb3540e0aaec47cfde0abf784c213f9216eecommit | diff
server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix values cast to int. Add Process-Start-Time-Unix header. (#5937)

Closes #5850
examples/server/server.cpp diff | blob | history
examples/server/tests/features/server.feature diff | blob | history
examples/server/tests/features/steps/steps.py diff | blob | history
Packaging of ggml-org/llama.cpp