Increase 3B scratch buffers. (#1698)

The 128 MB was too optimistic.
Too bad it is not dynamically computed.

diff --git a/llama.cpp b/llama.cpp
index 69bfdc1a107b512ecc444cf072d8d8cdb6dd479c..a16450173453a75622f6140ed16899b3dde5ced9 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -63,7 +63,7 @@ static const size_t MB = 1024*1024;
 static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
 {
     static std::map<e_model, size_t> k_sizes = {
-        { MODEL_3B,    128ull * MB },
+        { MODEL_3B,    256ull * MB },
         { MODEL_7B,    512ull * MB },
         { MODEL_13B,   512ull * MB },
         { MODEL_30B,   512ull * MB },
@@ -75,7 +75,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
 static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
 {
     static std::map<e_model, size_t> k_sizes = {
-        { MODEL_3B,    128ull * MB },
+        { MODEL_3B,    256ull * MB },
         { MODEL_7B,    512ull * MB },
         { MODEL_13B,   512ull * MB },
         { MODEL_30B,   512ull * MB },