ollama/llm/patches/03-load_exception.diff

58 lines
1.7 KiB
Diff
Raw Normal View History

2024-05-23 21:16:26 +00:00
From 544a2d2e646d39e878d87dfbb3398a356bc560ab Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me>
Date: Thu, 23 May 2024 11:18:45 -0700
Subject: [PATCH] throw exception on load errors
---
llama.cpp | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/llama.cpp b/llama.cpp
2024-05-23 21:16:26 +00:00
index 15c66077..8ba90b6a 100644
--- a/llama.cpp
+++ b/llama.cpp
2024-05-23 21:16:26 +00:00
@@ -6346,7 +6346,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
}
} catch (const std::exception & err) {
LLAMA_LOG_ERROR("%s: error loading model: %s\n", __func__, err.what());
- return -1;
+ throw;
}
return 0;
2024-05-23 21:16:26 +00:00
@@ -15600,16 +15600,23 @@ struct llama_model * llama_load_model_from_file(
}
model->rpc_servers.push_back(servers);
}
- int status = llama_model_load(path_model, *model, params);
- GGML_ASSERT(status <= 0);
- if (status < 0) {
- if (status == -1) {
- LLAMA_LOG_ERROR("%s: failed to load model\n", __func__);
- } else if (status == -2) {
- LLAMA_LOG_INFO("%s: cancelled model load\n", __func__);
2024-05-23 21:16:26 +00:00
+
+ try {
+ int status = llama_model_load(path_model, *model, params);
+ GGML_ASSERT(status <= 0);
+ if (status < 0) {
+ if (status == -1) {
+ LLAMA_LOG_ERROR("%s: failed to load model\n", __func__);
+ } else if (status == -2) {
+ LLAMA_LOG_INFO("%s: cancelled model load\n", __func__);
+ }
+ delete model;
+ return nullptr;
}
+ } catch (...) {
+ LLAMA_LOG_ERROR("%s: exception loading model\n", __func__);
delete model;
- return nullptr;
+ throw;
}
return model;
2024-05-23 21:16:26 +00:00
--
2.45.1