Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
Qwen3-8B-DMS-8x
like
34
Follow
NVIDIA
56.3k
Transformers
Safetensors
PyTorch
open-r1/OpenR1-Math-220k
qwen3
nvidia
kvcache
custom_code
text-generation-inference
arxiv:
5 papers
License:
nvidia-license
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (0)
Sort: Recently created
Triton kernel optimizations for DMS prefill path (up to 1.65x speedup)
#1 opened about 1 month ago by
amiga1200
amiga1200