]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a1a69f7)
server: expose prompt token counts in /slots endpoint (#23454)
authorScrewTSW <redacted>
Thu, 21 May 2026 11:29:13 +0000 (13:29 +0200)
committerGitHub <redacted>
Thu, 21 May 2026 11:29:13 +0000 (13:29 +0200)
commitb65bb4baaeae712975e09a92e1d37d3842ea5da7
tree5351603e140549a1e8415b71ffe7017c796cc2dbtree
parenta1a69f777a14bb8584ba0eb53505cd5ee888bd5ecommit | diff
server: expose prompt token counts in /slots endpoint (#23454)

Add n_prompt_tokens, n_prompt_tokens_processed, and n_prompt_tokens_cache
to the /slots JSON response. These fields are already tracked internally
but were not exposed, making it impossible for clients to monitor prompt
evaluation progress during processing.
tools/server/server-context.cpp diff | blob | history
Packaging of ggml-org/llama.cpp