From: Yoshi Suhara <redacted>
Date: Sat, 17 Aug 2024 13:34:21 +0000 (-0700)
Subject: Fix incorrect use of ctx_split for bias tensors (#9063)
X-Git-Tag: upstream/0.0.4488~887
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=2fb9267887d24a431892ce4dccc75c7095b0d54d;p=pkg%2Fggml%2Fsources%2Fllama.cpp

Fix incorrect use of ctx_split for bias tensors (#9063)
---

diff --git a/src/llama.cpp b/src/llama.cpp
index 7e9149eb..5ab65ea9 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -6172,9 +6172,9 @@ static bool llm_load_tensors(
                             layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
 
                             // optional MLP bias
-                            layer.ffn_gate_b = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "bias", i), {n_ff}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                            layer.ffn_down_b = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                            layer.ffn_up_b   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "bias", i), {n_ff}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                            layer.ffn_gate_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE, "bias", i), {n_ff}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                            layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                            layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i), {n_ff}, llama_model_loader::TENSOR_NOT_REQUIRED);
                         } else {
                             layer.ffn_gate_inp = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert});
 
@@ -6498,7 +6498,7 @@ static bool llm_load_tensors(
                         layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias",   i), {n_embd_gqa});
 
                         layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); //output_dens
-                        layer.bo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "bias",   i), {n_embd}); //output_dens
+                        layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias",   i), {n_embd}); //output_dens
 
                         layer.attn_out_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}); //output_norm
                         layer.attn_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "bias",   i), {n_embd});