aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2023-04-24 18:47:03 +0300
committerGeorgi Gerganov <ggerganov@gmail.com>2023-04-24 18:47:30 +0300
commit957c8ae21d1e7052ea45a40ee8c0407b909e90cc (patch)
tree625e674e806d07a36f76818cd1ea65718886c25a
parent9b0a4d421459f4e5e1af735c9784c3247b379025 (diff)
llama : increase scratch buffer size for 65B (ref #1152)
Temporary solution
-rw-r--r--llama.cpp4
1 files changed, 2 insertions, 2 deletions
diff --git a/llama.cpp b/llama.cpp
index bc0ef12..28d2791 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -54,7 +54,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
{ MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB },
- { MODEL_65B, 512ull * MB },
+ { MODEL_65B, 1024ull * MB },
};
return _MEM_REQ_SCRATCH0;
}
@@ -65,7 +65,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
{ MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB },
- { MODEL_65B, 512ull * MB },
+ { MODEL_65B, 1024ull * MB },
};
return _MEM_REQ_SCRATCH1;
}