- 02 Sep, 2025 1 commit
-
-
PanZezhong1725 authored
issue/37 - fixed an inappropriate qk buffer slicing
-
- 01 Sep, 2025 1 commit
-
-
wooway777 authored
-
- 21 Aug, 2025 1 commit
-
-
PanZezhong1725 authored
issue/29 - fixing tensor length mismatches across requests
-
- 20 Aug, 2025 4 commits
-
-
wooway777 authored
-
wooway777 authored
-
PanZezhong1725 authored
issue/27 - fixed slicing for req offset
-
wooway777 authored
-
- 19 Aug, 2025 1 commit
-
-
PanZezhong1725 authored
-
- 14 Aug, 2025 3 commits
-
-
PanZezhong authored
-
PanZezhong1725 authored
增加 Perplexity 测试脚本
-
PanZezhong authored
-
- 11 Aug, 2025 4 commits
-
-
PanZezhong1725 authored
Issue/21 - Inference Process Modualization
-
wooway777 authored
-
Pan Zezhong authored
-
wooway777 authored
-
- 08 Aug, 2025 5 commits
- 31 Jul, 2025 1 commit
-
-
wooway777 authored
-
- 30 Jul, 2025 1 commit
-
-
wooway777 authored
-
- 24 Jul, 2025 2 commits
-
-
PanZezhong1725 authored
issue/16: 多请求多并发测试脚本
-
Catheriany authored
-
- 23 Jul, 2025 3 commits
- 22 Jul, 2025 2 commits
-
-
wooway777 authored
-
PanZezhong authored
-
- 21 Jul, 2025 1 commit
-
-
wooway777 authored
-
- 18 Jul, 2025 1 commit
-
-
wooway777 authored
-
- 16 Jul, 2025 2 commits
-
-
PanZezhong1725 authored
support iluvatar device type
-
zhangyue authored
-
- 10 Jul, 2025 4 commits
-
-
PanZezhong1725 authored
fix: assign scale_* as class members instead of local variables
-
mxCynic authored
-
PanZezhong1725 authored
fix: fix 9G4B model by add coefficent to weight tensor when load
-
mxCynic authored
-
- 09 Jul, 2025 2 commits
-
-
mxCynic authored
-
PanZezhong authored
-
- 08 Jul, 2025 1 commit
-
-
Catheriany authored
-