sync : llama.cpp

ggerganov · ggerganov · commit bca51b528820 · 2024-01-14T10:49:50.000+02:00
diff --git a/examples/common-ggml.cpp b/examples/common-ggml.cpp
@@ -184,7 +184,7 @@ bool ggml_common_quantize_0(
                 case GGML_TYPE_Q5_K:
                 case GGML_TYPE_Q6_K:
                     {
-                        cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements, hist_cur.data());
+                        cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], hist_cur.data(), nullptr);
                     } break;
                 case GGML_TYPE_F32:
                 case GGML_TYPE_F16:
diff --git a/scripts/sync-llama.last b/scripts/sync-llama.last
@@ -1 +1 @@
-c71d608ce7a1584bf5072f197919dd24f3a6163f
+5f5fe1bd608fa2ed42af97b5f2ea31be6625fc48

Original file line number	Diff line number	Diff line change
`@@ -184,7 +184,7 @@ bool ggml_common_quantize_0(`
`184`	`184`	`case GGML_TYPE_Q5_K:`
`185`	`185`	`case GGML_TYPE_Q6_K:`
`186`	`186`	`{`
`187`		`- cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements, hist_cur.data());`
	`187`	`+ cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], hist_cur.data(), nullptr);`
`188`	`188`	`} break;`
`189`	`189`	`case GGML_TYPE_F32:`
`190`	`190`	`case GGML_TYPE_F16:`