CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

webui: updated the chat service to only include max_tokens in the req… (#16489)

Browse Source 
* webui: updated the chat service to only include max_tokens in the request payload when the setting is explicitly provided, while still mapping explicit zero or null values to the infinite-token sentinel

* chore: update webui build output
This commit is contained in:
Pascal
2025-10-09 22:54:57 +02:00
committed by GitHub
parent 1deee0f8d4
commit 1faa13a118
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
tools/server/public/index.html.gz
View File

Binary file not shown.

7
tools/server/webui/src/lib/services/chat.ts
View File

@@ -122,9 +122,10 @@ export class ChatService {
requestBody.reasoning_format = currentConfig.disableReasoningFormat ? 'none' : 'auto';
if (temperature !== undefined) requestBody.temperature = temperature;
// Set max_tokens to -1 (infinite) if not provided or empty
requestBody.max_tokens =
max_tokens !== undefined && max_tokens !== null && max_tokens !== 0 ? max_tokens : -1;
if (max_tokens !== undefined) {
// Set max_tokens to -1 (infinite) when explicitly configured as 0 or null
requestBody.max_tokens = max_tokens !== null && max_tokens !== 0 ? max_tokens : -1;
}
if (dynatemp_range !== undefined) requestBody.dynatemp_range = dynatemp_range;
if (dynatemp_exponent !== undefined) requestBody.dynatemp_exponent = dynatemp_exponent;