- 06 Mar, 2025 4 commits
-
-
liam authored
🚑 Merge branch 'develop-0.2.3' of https://github.com/kvcache-ai/ktransformers into develop-0.2.3 -
Azure authored
-
liam authored
-
Azure authored
-
- 05 Mar, 2025 7 commits
- 04 Mar, 2025 1 commit
-
-
liam authored
-
- 03 Mar, 2025 2 commits
- 02 Mar, 2025 3 commits
-
-
wang jiahao authored
fix typo for top_p
-
wang jiahao authored
fix ollama api temperature bug
-
1668068727@qq.com authored
-
- 01 Mar, 2025 15 commits
-
-
Wix Woo authored
-
Atream authored
Update:Solve `torch.backends.cuda.sdp_kernel()` is deprecated.
-
Atream authored
-
Atream authored
Update local_chat.py
-
moonshadow-25 authored
-
moonshadow-25 authored
-
宁鹏涛 authored
修复config.architectures[0] == "DeepseekV2ForCausalLM" or "DeepseekV3ForCausalLM" 永远为真
-
moonshadow-25 authored
-
godrosev authored
-
godrosev authored
-
Atream authored
Update DeepseekR1_V3_tutorial.md
-
Atream authored
-
Atream authored
Support chunk prefill. Support 139K context for DeepSeek-R1 139K with in 24G VRAM.
-
Atream authored
-
Atream authored
-
- 28 Feb, 2025 8 commits
-
-
ZiWei Yuan authored
fix cache_lens bug in server and rm test prompt.txt
-
-
liam authored
-
Atream authored
Delete duplicate code
-
liam authored
-
ZiWei Yuan authored
⚡ fox docker build -
liam authored
-
Azure authored
[fix] Fix template name
-
