Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
simonlesaumon
/
qwen-speedlab
like
0
Text Generation
English
qwen
qwen3.6
inference
llama.cpp
speculative-decoding
mtp
dflash
turboquant
rtx-3090
optimization
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
qwen-speedlab
/
kernels
49.3 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
simonlesaumon
Add custom CUDA kernels + demo scripts
727757f
verified
7 days ago
Makefile
1.57 kB
Add custom CUDA kernels + demo scripts
7 days ago
README.md
1.51 kB
Add custom CUDA kernels + demo scripts
7 days ago
benchmark.cu
6.41 kB
Add custom CUDA kernels + demo scripts
7 days ago
gdn_conv1d_warp.cu
10.7 kB
Add custom CUDA kernels + demo scripts
7 days ago
gdn_fused_proj.cu
12.1 kB
Add custom CUDA kernels + demo scripts
7 days ago
mtp_fused_verify.cu
11 kB
Add custom CUDA kernels + demo scripts
7 days ago
speedlab_kernels.h
6 kB
Add custom CUDA kernels + demo scripts
7 days ago
