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

llama : disable Direct IO by default (#19109)

Browse source 
* llama : disable Direct IO by default

* cont : override mmap if supported
This commit is contained in:
Georgi Gerganov 2026-01-28 09:11:13 +02:00 • committed by GitHub
parent eef375ce16
commit c5c64f72ac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 10 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

7
common/arg.cpp
View file

@ -2198,18 +2198,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
add_opt(common_arg(
{"--mmap"},
{"--no-mmap"},
string_format("whether to memory-map model. Explicitly enabling mmap disables direct-io. (if mmap disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
string_format("whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
[](common_params & params, bool value) {
params.use_mmap = value;
if (value) {
params.use_direct_io = false; // disable direct io when mmap is explicitly enabled
}
}
).set_env("LLAMA_ARG_MMAP"));
add_opt(common_arg(
{"-dio", "--direct-io"},
{"-ndio", "--no-direct-io"},
string_format("use DirectIO if available. Takes precedence over --mmap (default: %s)", params.use_direct_io ? "enabled" : "disabled"),
string_format("use DirectIO if available. (default: %s)", params.use_direct_io ? "enabled" : "disabled"),
[](common_params & params, bool value) {
params.use_direct_io = value;
}

2
common/common.h
View file

@ -438,7 +438,7 @@ struct common_params {
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool use_mmap = true; // enable mmap to use filesystem cache
bool use_direct_io = true; // read from disk without buffering for faster model loading
bool use_direct_io = false; // read from disk without buffering
bool use_mlock = false; // use mlock to keep model in memory
bool verbose_prompt = false; // print prompt tokens before generation
bool display_prompt = true; // print prompt before generation