]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 64fe17f)
server: fix correct time_ms calculation in prompt_progress (#17093)
authorAidan <redacted>
Sat, 8 Nov 2025 13:12:11 +0000 (13:12 +0000)
committerGitHub <redacted>
Sat, 8 Nov 2025 13:12:11 +0000 (15:12 +0200)
commiteeee367de51fb34d46c8103fc0ae827e84d94470
tree14d1da34910ce0c871bfa49ed1edb94608ae3db7tree
parent64fe17fbb84f493dbc33e4c13042953c4f5bfaebcommit | diff
server: fix correct time_ms calculation in prompt_progress (#17093)

* fix: correct time_ms calculation in send_partial_response

The time_ms field was incorrectly calculated. The division was happening
before the subtraction leading to incorrect values.

Before: (ggml_time_us() - slot.t_start_process_prompt / 1000) After:
(ggml_time_us() - slot.t_start_process_prompt) / 1000

* docs : document time_ms field in prompt_progress
tools/server/README.md diff | blob | history
tools/server/server.cpp diff | blob | history
Packaging of ggml-org/llama.cpp