Generate graph plots

diff --git a/llama.cpp b/llama.cpp
index 3413288..7578bfa 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -2311,7 +2311,7 @@ static struct ggml_cgraph * llm_build_llama(
     }
     ggml_set_name(KQ_scale, "1/sqrt(n_embd_head)");
 
-    for (int il = 0; il < n_layer; ++il) {
+    for (int il = 0; il < 1; ++il) {
         ggml_format_name(inpL, "layer_inp_%d", il);
 
         offload_func_t offload_func = llama_nop;
@@ -2993,9 +2993,10 @@ static bool llama_eval_internal(
 #endif
 
     // plot the computation graph in dot format (for debugging purposes)
-    //if (n_past%100 == 0) {
-    //    ggml_graph_dump_dot(gf, NULL, "llama.dot");
-    //}
+    //if (N == 7) {
+    if (n_past%45 == 0) {
+        ggml_graph_dump_dot(gf, NULL, "llama.dot");
+    }
 
     // extract logits
     {

Note: n_past is now replaced with batch.pos[]

LLaMAv2 7B, n_past == 45, n_batch == 1

LLaMAv2 7B, n_past == 0, n_batch == 7

LLaMAv2 7B, n_past == 4, n_batch == 3

Users Guide

Useful information for users that doesn't fit into Readme.

Technical Details

These are information useful for Maintainers and Developers which does not fit into code comments

Github Actions Main Branch Status

Click on a badge to jump to workflow. This is here as a useful general view of all the actions so that we may notice quicker if main branch automation is broken and where.