8000 quantize: improve pattern matching for allowed tensors by EAddario · Pull Request #13033 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

quantize: improve pattern matching for allowed tensors #13033

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
May 13, 2025
Merged

quantize: improve pattern matching for allowed tensors #13033

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
6c281ad
Move struct declaration to header and update allowed tensor list
EAddario Apr 17, 2025
3e031bc
Improve regex matching whilst still validating allowed tensors
EAddario Apr 17, 2025
6c13fcb
Minor cosmetic change to log output
EAddario Apr 17, 2025
16923b8
Merge branch 'master' into quantize
EAddario Apr 19, 2025
d54a423
Merge branch 'master' into quantize
EAddario May 3, 2025
d69391e
Add header search path
EAddario May 3, 2025
70daa41
Merge branch 'master' into quantize
EAddario May 11, 2025
61bb6e2
Remove allowed tensor checks
EAddario May 11, 2025
184ef70
Remove unneeded include directory
EAddario May 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Minor cosmetic change to log output
  • Loading branch information
@EAddario
EAddario committed Apr 17, 2025
commit 6c13fcbc30a785559f79dd25bd1039df264dc0f5
2 changes: 1 addition & 1 deletion src/llama-quant.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -796,7 +796,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
for (const auto & allowed : ALLOWED_TENSOR_TYPE) {
if (tensor_name.find(allowed) != std::string::npos) {
if (qtype != new_type) {
LLAMA_LOG_DEBUG("(overriding %s), ", ggml_type_name(new_type));
LLAMA_LOG_DEBUG("(overriding %s) ", ggml_type_name(new_type));
new_type = qtype;
break;
}
Expand Down
0