- 07 Feb, 2025 1 commit
-
-
Azure authored
-
- 06 Feb, 2025 1 commit
-
-
Azure authored
-
- 04 Feb, 2025 1 commit
-
-
Azure authored
-
- 01 Feb, 2025 1 commit
-
-
Azure authored
-
- 31 Jan, 2025 1 commit
-
-
Azure authored
-
- 12 Sep, 2024 1 commit
-
-
xhedit authored
-
- 29 Aug, 2024 1 commit
-
-
TangJingqi authored
-
- 28 Aug, 2024 1 commit
-
-
chenxl authored
-
- 15 Aug, 2024 1 commit
-
-
TangJingqi authored
-
- 14 Aug, 2024 1 commit
-
-
Atream authored
[fix] fix ktransformers interface when use new CUDAGraphRunner [fix] fix YAML and optimize logic, the top rule has the highest priority
-
- 12 Aug, 2024 1 commit
-
-
chenxl authored
-
- 08 Aug, 2024 3 commits
-
-
chenht2022 authored
1) Linear and MLP operators support qlen>1; 2) All operators now share a single memory buffer; 3) Refactor CPUInfer submit/sync logic.
-
Atream authored
-
Atream authored
support windows support q4_0 and q5_0 dequant on cpu Add CopyRight from pygguf(It was added before, but disappear after merge). Add some TODO in the code.
-
- 27 Jul, 2024 1 commit
-
-
chenxl authored
-
