]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0da5d86)
server: bench: minor fixes (#10765)
authorPierrick Hymbert <redacted>
Thu, 2 Jan 2025 17:06:12 +0000 (18:06 +0100)
committerGitHub <redacted>
Thu, 2 Jan 2025 17:06:12 +0000 (18:06 +0100)
commit2f0ee84b9b02d2a98742308026f060ebdc2423f1
treec7a2ab087f640da24e9c5f2cf5f2f4856e00bd54tree
parent0da5d860266c6928b8c9408efbd264ae59fedda6commit | diff
server: bench: minor fixes (#10765)

* server/bench:
- support openAI streaming standard output with [DONE]\n\n
- export k6 raw results in csv
- fix too many tcp idle connection in tcp_wait
- add metric time to emit first token

* server/bench:
- fix when prometheus not started
- wait for server to be ready before starting bench
examples/server/bench/README.md diff | blob | history
examples/server/bench/bench.py diff | blob | history
examples/server/bench/script.js diff | blob | history
Packaging of ggml-org/llama.cpp