ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 16:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Llama-quantize: Partial requant feature (#1313)

Browse Source 
* Partial Requant feature for llama-quantize

- Inspired by the recently portcopied --dry-run feature.
- Allows to partially requantize a split quantized .gguf by requantizing only the missing splits in the destination directory.
- Works both for GGUF which are split tensors by tensors, or by group of several tensors (though this one is not very much tested beyond 2 tensors by split).
- Vibe coded.

* Create output directory if it doesn't exist in llama-quantize

* Create output directory if it doesn't exist in gguf-split

* Add exit when directory fails to be created on Windows

* Use std::filesystem

* cleanup
This commit is contained in:
Nexes the Elder
2026-02-25 07:25:15 +01:00
committed by GitHub
parent 68431b049a
commit 170467e835
5 changed files with 69 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/quantize/quantize.cpp
View File

@@ -151,7 +151,7 @@ static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftyp
//
[[noreturn]]
static void usage(const char * executable) {
printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] [--pure] [--imatrix] [--hide-imatrix] [--include-weights] [--exclude-weights] [--output-tensor-type] [--token-embedding-type] [--ffn-gate-inp-type] [--attn-q-type] [--attn-k-type] [--attn-v-type] [--attn-qkv-type] [--attn-output-type] [--ffn-gate-type] [--ffn-down-type] [--ffn-up-type] [--keep-split] [--override-kv] model-f32.gguf [model-quant.gguf] type [nthreads]\n\n", executable);
printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] [--pure] [--imatrix] [--hide-imatrix] [--include-weights] [--exclude-weights] [--output-tensor-type] [--token-embedding-type] [--ffn-gate-inp-type] [--attn-q-type] [--attn-k-type] [--attn-v-type] [--attn-qkv-type] [--attn-output-type] [--ffn-gate-type] [--ffn-down-type] [--ffn-up-type] [--keep-split] [--partial-requant] [--override-kv] model-f32.gguf [model-quant.gguf] type [nthreads]\n\n", executable);
printf(" --allow-requantize: Allows requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit\n");
printf(" --leave-output-tensor: Will leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing\n");
printf(" --pure: Disable k-quant mixtures and quantize all tensors to the same type\n");
@@ -175,6 +175,7 @@ static void usage(const char * executable) {
printf(" --ffn-down-type ggml_type: use this ggml_type for the ffn_down tensor.\n");
printf(" --ffn-up-type ggml_type: use this ggml_type for the ffn_up tensor.\n\n");
printf(" --keep-split: will generate quantized model in the same shards as input\n");
printf(" --partial-requant: quantize only missing split files in the split quantized .gguf destination directory\n");
printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n\n");
printf("Note: --include-weights and --exclude-weights cannot be used together\n");
@@ -466,6 +467,8 @@ int main(int argc, char ** argv) {
}
} else if (strcmp(argv[arg_idx], "--keep-split") == 0) {
params.keep_split = true;
} else if (strcmp(argv[arg_idx], "--partial-requant") == 0) {
params.partial_requant = true;
} else {
usage(argv[0]);
}