tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : throw an error when slot unavailable (#4741)

Browse Source
This commit is contained in:
Justin Parker
2024-01-03 03:43:19 -05:00
committed by GitHub
parent f3f62f0d83
commit f2eb19bd8b
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/server/public/completion.js
View File

@@ -95,6 +95,15 @@ export async function* llama(prompt, params = {}, config = {}) {
break; break;
} }
} }
if (result.error) {
result.error = JSON.parse(result.error);
if (result.error.content.includes('slot unavailable')) {
// Throw an error to be caught by upstream callers
throw new Error('slot unavailable');
} else {
console.error(`llama.cpp error: ${result.error.content}`);
}
}
if (result.error) { if (result.error) {
result.error = JSON.parse(result.error); result.error = JSON.parse(result.error);
console.error(`llama.cpp error: ${result.error.content}`); console.error(`llama.cpp error: ${result.error.content}`);