]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
server: allow accessing /metrics and /slots during llama_decode() (#27041)
authorXuan-Son Nguyen <redacted>
Fri, 14 Aug 2026 11:23:10 +0000 (13:23 +0200)
committerGitHub <redacted>
Fri, 14 Aug 2026 11:23:10 +0000 (13:23 +0200)
commit77918caf30e65f830ab0759c89779efdac28c77b
tree560218f5fd6a80f5a3f5601a6ffa636450dad212
parent885c5bbe8e04dc78db25beb911a2715312ad7b54
server: allow accessing /metrics and /slots during llama_decode() (#27041)

* server_queue::worker

* call llama_decode inside yield_to_queue

* also handle process_mtmd_chunk

* clean up

* nits

* rm test
tools/server/server-context.cpp
tools/server/server-queue.cpp
tools/server/server-queue.h