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

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

Browse source 
* llama: automatically fit args to free memory

llama-fit-params tool

* fix CI

* hints for bug reports, ensure no reallocation

* fix segfault with Vulkan

* add llama-fit-params to CI

* fix CI

* fix CI

* fix CI

* minor adjustments

* fix assignment of 1 dense layer

* fix logger not being reset on model load failure

* remove --n-gpu-layer hint on model load failure

* fix llama-fit-params verbosity

* fix edge case

* fix typo [no ci]
This commit is contained in:
Johannes Gäßler 2025-12-15 09:24:59 +01:00 • committed by GitHub
parent 4aced7a631
commit b1f3a6e5db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 1075 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

33
common/arg.cpp
View file

@ -20,6 +20,7 @@
#include <nlohmann/json.hpp>
#include <algorithm>
#include <cinttypes>
#include <climits>
#include <cstdarg>
#include <fstream>
@ -529,7 +530,9 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
params.kv_overrides.back().key[0] = 0;
}
if (!params.tensor_buft_overrides.empty()) {
// pad tensor_buft_overrides for llama_params_fit:
const size_t ntbo = llama_max_tensor_buft_overrides();
while (params.tensor_buft_overrides.size() < ntbo) {
params.tensor_buft_overrides.push_back({nullptr, nullptr});
}
@ -2153,6 +2156,34 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_env("LLAMA_ARG_MAIN_GPU"));
add_opt(common_arg(
{ "-fit", "--fit" }, "[on|off]",
string_format("whether to adjust unset arguments to fit in device memory ('on' or 'off', default: '%s')", params.fit_params ? "on" : "off"),
[](common_params & params, const std::string & value) {
if (is_truthy(value)) {
params.fit_params = true;
} else if (is_falsey(value)) {
params.fit_params = false;
} else {
throw std::runtime_error(
string_format("error: unkown value for --fit: '%s'\n", value.c_str()));
}
}
).set_env("LLAMA_ARG_FIT"));
add_opt(common_arg(
{ "-fitt", "--fit-target" }, "MiB",
string_format("target margin per device for --fit option, default: %zu", params.fit_params_target/(1024*1024)),
[](common_params & params, int value) {
params.fit_params_target = value * size_t(1024*1024);
}
).set_env("LLAMA_ARG_FIT_TARGET"));
add_opt(common_arg(
{ "-fitc", "--fit-ctx" }, "N",
string_format("minimum ctx size that can be set by --fit option, default: %" PRIu32, params.fit_params_min_ctx),
[](common_params & params, int value) {
params.fit_params_min_ctx = value;
}
).set_env("LLAMA_ARG_FIT_CTX"));
add_opt(common_arg(
{"--check-tensors"},
string_format("check model tensor data for invalid values (default: %s)", params.check_tensors ? "true" : "false"),