PrototypeCommon
AlibabaResearch/flash-llm
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
- Owner
- AlibabaResearch (organization)
- Stars
- Stars: 246
- Forks
- Forks: 24
- Language
- Cuda
- License
- Apache-2.0
- Created
- 2023
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by AlibabaResearch
All 6 repos by AlibabaResearch- AlibabaResearch/AdvancedLiterateMachineryStars: 1,834C++Beta
- AlibabaResearch/DAMO-ConvAIStars: 1,618PythonBeta
- AlibabaResearch/efficientteacherStars: 814PythonBeta
- AlibabaResearch/SparkDiffusionStars: 572PythonAlpha
- AlibabaResearch/abenchStars: 151PythonPrototype
Nearby in Cuda
All Cuda repos- NVlabs/CGBNStars: 253CudaAlpha
- zhai-xiao/CPP-Fluid-ParticlesStars: 250CudaAlpha
- ZaidQureshi/bamStars: 249CudaPrototype
- rahul-goel/fused-ssimStars: 245CudaPrototype
- OpenBMB/CPM.cuStars: 243CudaPrototype
- vernamlab/cuFHEStars: 240CudaPrototype