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

llama : add use_direct_io flag for model loading (#18166)

Browse source 
* Adding --direct-io flag for model loading

* Fixing read_raw() calls

* Fixing Windows read_raw_at

* Changing type off_t to size_t for windows and Renaming functions

* disable direct io when mmap is explicitly enabled

* Use read_raw_unsafe when upload_backend is available, not functional on some devices with Vulkan and SYCL

* Fallback to std::fread in case O_DIRECT fails due to bad address

* Windows: remove const keywords and unused functions

* Update src/llama-mmap.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: jtischbein <jtischbein@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Julius Tischbein 2026-01-08 07:35:30 +01:00 • committed by GitHub
parent 568371a726
commit 2038101bd9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 118 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -309,6 +309,7 @@ extern "C" {
// Keep the booleans together to avoid misalignment during copy-by-value.
bool vocab_only; // only load the vocabulary, no weights
bool use_mmap; // use mmap if possible
bool use_direct_io; // use direct io, takes precedence over use_mmap
bool use_mlock; // force system to keep model in RAM
bool check_tensors; // validate model tensor data
bool use_extra_bufts; // use extra buffer types (used for weight repacking)