sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 107 Packages Projects Releases Wiki Activity

server: rename --clear-idle to --cache-idle-slots (#21741)

Browse Source
This commit is contained in:
Yes You Can Have Your Own
2026-04-20 08:30:24 +03:00
committed by GitHub
parent e365e658f0
commit 9d49acb2a7
6 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+4 -4
View File
@@ -1316,13 +1316,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_BATCHED, LLAMA_EXAMPLE_BENCH, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"--clear-idle"},
{"--no-clear-idle"},
{"--cache-idle-slots"},
{"--no-cache-idle-slots"},
"save and clear idle slots on new task (default: enabled, requires unified KV and cache-ram)",
[](common_params & params, bool value) {
params.clear_idle = value;
params.cache_idle_slots = value;
}
).set_env("LLAMA_ARG_CLEAR_IDLE").set_examples({LLAMA_EXAMPLE_SERVER}));
).set_env("LLAMA_ARG_CACHE_IDLE_SLOTS").set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--context-shift"},
{"--no-context-shift"},
common/common.h
+1 -1
View File
@@ -567,7 +567,7 @@ struct common_params {
int32_t n_threads_http = -1; // number of threads to process HTTP requests (TODO: support threadpool)
int32_t n_cache_reuse = 0; // min chunk size to reuse from the cache via KV shifting
bool cache_prompt = true; // whether to enable prompt caching
bool clear_idle = true; // save and clear idle slots upon starting a new task
bool cache_idle_slots = true; // save and clear idle slots upon starting a new task
int32_t n_ctx_checkpoints = 32; // max number of context checkpoints per slot
int32_t checkpoint_every_nt = 8192; // make a checkpoint every n tokens during prefill
int32_t cache_ram_mib = 8192; // -1 = no limit, 0 - disable, 1 = 1 MiB, etc.