rm redundant code

ngxson · ngxson · commit 6692656dc5d8 · 2025-06-29T22:38:44.000+02:00
diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp
@@ -894,9 +894,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
             if (params->token_embedding_type < GGML_TYPE_COUNT && strcmp(tensor->name, "token_embd.weight") == 0) {
                 new_type = params->token_embedding_type;
             }
-            if (params->token_embedding_type < GGML_TYPE_COUNT && strcmp(tensor->name, "per_layer_token_embd.weight") == 0) {
-                new_type = params->token_embedding_type;
-            }
             if (params->output_tensor_type < GGML_TYPE_COUNT && strcmp(tensor->name, "output.weight") == 0) {
                 new_type = params->output_tensor_type;
             }

Original file line number	Diff line number	Diff line change
`@@ -894,9 +894,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::`
`894`	`894`	`if (params->token_embedding_type < GGML_TYPE_COUNT && strcmp(tensor->name, "token_embd.weight") == 0) {`
`895`	`895`	`new_type = params->token_embedding_type;`
`896`	`896`	`}`
`897`		`- if (params->token_embedding_type < GGML_TYPE_COUNT && strcmp(tensor->name, "per_layer_token_embd.weight") == 0) {`
`898`		`- new_type = params->token_embedding_type;`
`899`		`- }`
`900`	`897`	`if (params->output_tensor_type < GGML_TYPE_COUNT && strcmp(tensor->name, "output.weight") == 0) {`
`901`	`898`	`new_type = params->output_tensor_type;`
`902`	`899`	`}`