AlphaUncommon
SakanaAI/sparser-faster-llms
Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
- Owner
- SakanaAI (organization)
- Stars
- Stars: 263
- Forks
- Forks: 26
- Language
- Cuda
- License
- MIT
- Created
- 2026
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by SakanaAI
All 29 repos by SakanaAI- SakanaAI/AI-ScientistStars: 14,927Jupyter NotebookStable
- SakanaAI/AI-Scientist-v2Stars: 7,432PythonStable
- SakanaAI/continuous-thought-machinesStars: 2,045PythonRC
- SakanaAI/ShinkaEvolveStars: 1,493PythonBeta
- SakanaAI/evolutionary-model-mergeStars: 1,441PythonBeta
- SakanaAI/text-to-loraStars: 1,326PythonBeta
Nearby in Cuda
All Cuda repos- What-a-stupid-username/MRPNNStars: 267CudaAlpha
- yanchi-3dv/diff-gaussian-rasterization-for-gsslamStars: 267CudaAlpha
- AndreSlavescu/mHC.cuStars: 267CudaAlpha
- dnouri/cuda-convnetStars: 261CudaAlpha
- Dots-Infra/UltraEPStars: 260CudaAlpha
- R100001/Programming-Massively-Parallel-ProcessorsStars: 259CudaAlpha