mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 Packages Projects Releases Wiki Activity

quantize : add --dry-run option (#19526)

Browse Source 
* clean slate for branch

* use 6 characters for tensor dims

* add --dry-run to llama-quantize

* use 6 characters for tensor dims (cont.)

* no need to re-calculate ggml_nbytes for tensor

* fix indent

* show model and quant BPW when quant completes

* add example to --help

* new function `tensor_requires_imatrix`, add courtesy warning about imatrix

* missing __func__, move imatrix flag set

* logic error

* fixup tensor_requires_imatrix

* add missing `GGML_TYPE`s

* simplify and rename `tensor_type_requires_imatrix`

* simplify for style

* add back Q2_K edge case for imatrix

* guard ftype imatrix warning

* comment ref #12557

* remove per @compilade

* remove unused `params` parameter

* move `bool dry_run` per GG

* move `bool dry_run` per GG

* Update src/llama-quant.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-quant.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-quant.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
ddh0
2026-02-20 02:20:16 -06:00
committed by GitHub
parent 77d6ae4ac8
commit 492bc31978
4 changed files with 206 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-impl.cpp
+2 -2
View File
@@ -109,9 +109,9 @@ std::string llama_format_tensor_shape(const std::vector<int64_t> & ne) {
std::string llama_format_tensor_shape(const struct ggml_tensor * t) {
char buf[256];
snprintf(buf, sizeof(buf), "%5" PRId64, t->ne[0]);
snprintf(buf, sizeof(buf), "%6" PRId64, t->ne[0]);
for (int i = 1; i < GGML_MAX_DIMS; i++) {
snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), ", %5" PRId64, t->ne[i]);
snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf), ", %6" PRId64, t->ne[i]);
}
return buf;
}