How to run deepseek on Ada GPUs？Mine is L20.
#25 opened about 22 hours ago
by 
XiaoZaiyi
How can I use this with llama.cpp?
➕ 1
1
#24 opened 1 day ago
by 
KeilahElla
Should the "index_topk" be updated to 1024 just like the Pro model?
#23 opened 3 days ago
by 
jfcherng
Questions on MoE Hash Routing
#22 opened 3 days ago
by 
mattduerrmeier
120B model?
👍 3
1
#21 opened 3 days ago
by 
jacek2024
Run DeepSeek-V4-Flash on more hardware: FP8/BF16 adapted versions for 8 AI chips (ready to download)
👍 1
#20 opened 3 days ago
by 
Yonghua
[适配请求] 建议 API 兼容 OpenAI 新规范中的 developer 角色 （It is recommended that the API be compatible with the developer role in the new OpenAI specification
#19 opened 5 days ago
by 
xusu616
Update README.md to add SGLang deployment option
#18 opened 5 days ago
by 
zjxia
Is 158B or 284b params ?
6
#17 opened 5 days ago
by 
celsowm
Add chat template
🔥 3
5
#16 opened 5 days ago
by 
Rocketknight1
Unable to run on 2x RTX Pro 6000 (DEEP_GEMM problem)
➕ 7
10
#15 opened 5 days ago
by 
stev236
Local Installation Video and Testing - Step by Step
👍😔 4
#13 opened 6 days ago
by 
fahdmirzac
Too big to run locally.
🤯👍 9
9
#12 opened 6 days ago
by 
Dampfinchen
Add community evaluation results for GPQA, MMLU-PRO, SWE-BENCH_VERIFIED, HLE, TERMINAL-BENCH-2.0
#11 opened 6 days ago
by 
nielsr
May I ask if there is a deployment document?
2
#10 opened 6 days ago
by 
jerryliujiawei
Will there be a smaller model like Qwen3.5 122 or Nemotron 3 super
➕ 7
7
#9 opened 6 days ago
by 
mayankiit04
Maximum Thinking Token High vs Max?
#8 opened 6 days ago
by 
Miracle12345
起立，立正！
🔥 7
3
#5 opened 6 days ago
by 
lizhooh
Sick
#3 opened 6 days ago
by 
Green-eyedDevil
support inference by sglang or vllm ?
3
#2 opened 6 days ago
by 
howtain
Here comes the big one
🤗🔥 8
#1 opened 6 days ago
by 
huggingfacess