nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 23 Packages Projects Releases Wiki Activity

llama-quant : fix --tensor-type when default qtype is overriden (#22572)

Browse Source 
fix #22544 (my fault!)

Credit to @Anai-Guo, ref #22559 - since that one was closed due to the
new contributor policy I am taking the liberty of re-submitting that PR
here.
This commit is contained in:
ddh0
2026-05-01 19:55:55 +02:00
committed by GitHub
parent 2098fd6169
commit b97ebdc98f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+1 -1
View File
@@ -683,12 +683,12 @@ static ggml_type llama_tensor_get_type(quantize_state_impl & qs, const llama_mod
LLAMA_LOG_WARN("%s: %-36s - applying manual override: %s -> %s\n", LLAMA_LOG_WARN("%s: %-36s - applying manual override: %s -> %s\n",
__func__, tensor_name.c_str(), ggml_type_name(new_type), ggml_type_name(qtype)); __func__, tensor_name.c_str(), ggml_type_name(new_type), ggml_type_name(qtype));
new_type = qtype; new_type = qtype;
}
manual = true; manual = true;
break; break;
} }
} }
} }
}
// if not manual - use the standard logic for choosing the quantization type based on the selected mixture // if not manual - use the standard logic for choosing the quantization type based on the selected mixture
if (!manual) { if (!manual) {