mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 Packages Projects Releases Wiki Activity

Checkpoint every n tokens: squash (#20087)

Browse Source
This commit is contained in:
Piotr Wilkin (ilintar)
2026-03-06 11:39:26 +01:00
committed by GitHub
parent f6235a41ef
commit f5ddcd1696
3 changed files with 77 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+8 -1
View File
@@ -1279,13 +1279,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_SWA_FULL"));
add_opt(common_arg(
{"--ctx-checkpoints", "--swa-checkpoints"}, "N",
{"-ctxcp", "--ctx-checkpoints", "--swa-checkpoints"}, "N",
string_format("max number of context checkpoints to create per slot (default: %d)"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_ctx_checkpoints),
[](common_params & params, int value) {
params.n_ctx_checkpoints = value;
}
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-cpent", "--checkpoint-every-n-tokens"}, "N",
string_format("create a checkpoint every n tokens during prefill (processing), -1 to disable (default: %d)", params.checkpoint_every_nt),
[](common_params & params, int value) {
params.checkpoint_every_nt = value;
}
).set_env("LLAMA_ARG_CHECKPOINT_EVERY_NT").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-cram", "--cache-ram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)"
common/common.h
+9 -8
View File
@@ -516,14 +516,15 @@ struct common_params {
std::string cls_sep = "\t"; // separator of classification sequences
// server params
int32_t port = 8080; // server listens on this network port
int32_t timeout_read = 600; // http read timeout in seconds
int32_t timeout_write = timeout_read; // http write timeout in seconds
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
int32_t n_ctx_checkpoints = 8; // max number of context checkpoints per slot
int32_t cache_ram_mib = 8192; // -1 = no limit, 0 - disable, 1 = 1 MiB, etc.
int32_t port = 8080; // server listens on this network port
int32_t timeout_read = 600; // http read timeout in seconds
int32_t timeout_write = timeout_read; // http write timeout in seconds
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
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.
std::string hostname = "127.0.0.1";
std::string public_path = ""; // NOLINT