thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

spec : remove check rate (#19377)

Browse source 
* spec: remove parameter spec-ngram-check-rate

* spec : renamed statistics vars

* spec : add n_call_begin, n_call_accept

* spec : don't enable key-map-stats
This commit is contained in:
Sascha Rogmann 2026-02-09 14:30:50 +01:00 • committed by GitHub
parent 81ddc60cb3
commit 292f6908cd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 36 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

10
common/arg.cpp
View file

@ -3437,16 +3437,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.ngram_size_m = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--spec-ngram-check-rate"}, "N",
string_format("ngram check rate for ngram-simple/ngram-map speculative decoding (default: %d)", params.speculative.ngram_check_rate),
[](common_params & params, int value) {
if (value < 1) {
throw std::invalid_argument("ngram check rate must be at least 1");
}
params.speculative.ngram_check_rate = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--spec-ngram-min-hits"}, "N",
string_format("minimum hits for ngram-map speculative decoding (default: %d)", params.speculative.ngram_min_hits),