- 25 Feb, 2025 2 commits
- 24 Feb, 2025 3 commits
- 23 Feb, 2025 2 commits
- 22 Feb, 2025 8 commits
-
-
Azure authored
Add fp8 linear kernel;\n Add empty cache to fit in 16G VRAM; By 'wkGCaSS - 知乎 https://zhuanlan.zhihu.com/p/25491611225'
-
Atream authored
optimize CMake multi core parallel
-
Atream authored
Feat more context
-
Atream authored
-
Atream authored
Fix the link address in the doc install.md
-
Atream authored
Adjust the installation link to the correct section of docs
-
Atream authored
-
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
-
- 21 Feb, 2025 3 commits
-
-
_ authored
-
JiamingMai authored
-
Atream authored
-
- 20 Feb, 2025 8 commits
-
-
Azure authored
feat: Support Moore Threads GPU
-
ZiWei Yuan authored
Docker dev
-
liam authored
-
-
ZiWei Yuan authored
feat: add GitHub Actions workflow for building Docker image
-
liam authored
-
liam authored
-
miaooo0000OOOO authored
-
- 19 Feb, 2025 10 commits
-
-
Xiaodong Ye authored
Signed-off-by:Xiaodong Ye <xiaodong.ye@mthreads.com>
-
Atream authored
Necessary tips for Node.js related issues
-
Zhoneym authored
-
Atream authored
Add notes to DeepSeek-R1 tutorial documentation
-
Atream authored
clean PR code and disable flashinfer
-
Atream authored
-
Atream authored
fix server and add prefix cache for server
-
Azure authored
Modify and add any incorrect or missing content in the `install.md`
-
Zhoneym authored
-
Zhoneym authored
-
- 18 Feb, 2025 4 commits
-
-
ceerrep authored
-
ceerrep authored
-
ZiWei Yuan authored
🔖 release v0.2.1.post1 -
liam authored
-
