- 17 Mar, 2025 2 commits
- 14 Mar, 2025 1 commit
-
-
Atream authored
-
- 26 Feb, 2025 1 commit
-
-
Atream authored
-
- 22 Feb, 2025 1 commit
-
-
Atream authored
use marlin for lm_head, lm_head only calc last token for prefill extend context window to 19K for DeepSeek-V3/R1 within 24GB VRAM
-
- 12 Feb, 2025 1 commit
-
-
Azure authored
-
- 10 Feb, 2025 1 commit
-
-
liam authored
-
- 07 Feb, 2025 1 commit
-
-
Azure authored
-
- 04 Feb, 2025 1 commit
-
-
Azure authored
-
- 01 Feb, 2025 2 commits
- 31 Jan, 2025 1 commit
-
-
Azure authored
-
- 29 Aug, 2024 1 commit
-
-
TangJingqi authored
-
- 28 Aug, 2024 1 commit
-
-
chenxl authored
-
- 15 Aug, 2024 2 commits
-
-
TangJingqi authored
-
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
-