]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
server : consolidate slot selection into get_available_slot (#24755)
authorGeorgi Gerganov <redacted>
Fri, 19 Jun 2026 06:22:34 +0000 (09:22 +0300)
committerGitHub <redacted>
Fri, 19 Jun 2026 06:22:34 +0000 (09:22 +0300)
commit80452d65b9b1d44b496ed729f1fb0b6c4c39d7bf
tree94d568d7d5a7413b0fa93984d9a0dc4ff6942984
parent8141e730f1598780c19b153e0e212ed70a672c53
server : consolidate slot selection into get_available_slot (#24755)

Absorb get_slot_by_id logic into get_available_slot so slot selection
is handled by a single function call. When a specific slot id is
requested, the LCP similarity check still runs to enable proper
prompt cache updates.

Assisted-by: pi:llama.cpp/Qwen3.6-27B
tools/server/server-context.cpp