 Xiaohan-Tian
|
2bd6925f27
|
fix: switch to processing status when receiving response tokens from LLM
|
2026-05-14 21:37:06 -07:00 |
|
|
Xiaohan-Tian
|
1a051fea54
|
feat: added a welcome msg for local LLM users
|
2026-05-14 21:24:03 -07:00 |
|
|
Xiaohan-Tian
|
a48966d761
|
feat: added local LLM context length option
|
2026-05-14 19:44:25 -07:00 |
|
|
Xiaohan-Tian
|
dbf0c20542
|
fix: updated Gemma 4 URL from local test url to HF url
|
2026-05-14 19:33:44 -07:00 |
|
|
Xiaohan-Tian
|
6460d4ffa0
|
fix: initial global spinner randomly hanging until 10s timeout
|
2026-05-14 19:33:13 -07:00 |
|
|
Xiaohan-Tian
|
c7a1630862
|
fix: show cache loading progress
|
2026-05-14 19:12:36 -07:00 |
|
|
Xiaohan-Tian
|
eb1c7bd2fc
|
feat: added performance statistics info when using embedded LLM
|
2026-05-14 19:05:13 -07:00 |
|
|
Xiaohan-Tian
|
98c2b97413
|
feat: implemented the v1 browser embedded LLM support (Gemma 4 E4B based)
|
2026-05-14 18:55:23 -07:00 |
|
|
Xiaohan-Tian
|
0e6e2736d0
|
feat: added VSCode Windows debugging entry
|
2026-05-14 18:03:58 -07:00 |
|