CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

llava : fix memory management bug (#5491)

Browse Source 
* Fix memory management in llava and server code

Fixes this error:

llama_new_context_with_model: graph splits (measure): 3
Available slots:
 -> Slot 0 - max context: 6000
{"timestamp":1707926446,"level":"INFO","function":"main","line":2623,"message":"model loaded"}
all slots are idle and system prompt is empty, clear the KV cache
slot 0 - loaded image
slot 0 is processing [task id: 0]
slot 0 : kv cache rm - [0, end)
slot 0 - encoding image [id: 1]
munmap_chunk(): invalid pointer
Aborted

* Make it cleaner by checking size in batch free wrapper
This commit is contained in:
Elbios
2024-02-15 09:01:57 +01:00
committed by GitHub
parent 7930a8a6e8
commit 0d4177126b
3 changed files with 28 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/server/server.cpp
View File

@@ -975,7 +975,12 @@ struct llama_server_context
{
LOG_TEE("Error processing the given image");
clip_free(clp_ctx);
clip_image_f32_free(img_res_v.data);
clip_image_f32_batch_free(img_res_v);
return false;
}
if (img_res_v.size == 0)
{
LOG_TEE("Error processing the given image");
return false;
}
@@ -987,6 +992,7 @@ struct llama_server_context
if (!img.image_embedding)
{
LOG_TEE("Unable to allocate memory for image embeddings\n");
clip_image_f32_batch_free(img_res_v);
clip_free(clp_ctx);
return false;
}
@@ -994,10 +1000,11 @@ struct llama_server_context
if (!clip_image_encode(clp_ctx, params.n_threads, img_res, img.image_embedding))
{
LOG_TEE("Unable to encode image\n");
clip_image_f32_batch_free(img_res_v);
return false;
}
clip_image_f32_free(img_res_v.data);
clip_image_f32_batch_free(img_res_v);
img.request_encode_image = false;
}