Tim Dettmers
Staff Research Scientist, Ai2 | Creator of bitsandbytes & QLoRA Quantization
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Tim Dettmers. Every entry undergoes editorial source verification.
8-Bit Optimizers via Block-wise Dynamic Quantization with Low-Precision States
A breakthrough algorithmic paper by Tim Dettmers introducing 8-bit Adam and low-precision optimizer states, reducing memory consumption of deep learning training states by 75% without compromising model convergence.
Custom CUDA block-level quantization; optimizer speedups are maximized on modern Tensor Core architectures.
bitsandbytes: 8-Bit and 4-Bit CUDA Quantization Primitives
The open-source library behind 8-bit matrix multiplication and 4-bit NormalFloat quantization, enabling consumer GPUs to run and train 70B+ parameter foundation models with negligible accuracy loss.
Tightly coupled with NVIDIA CUDA architectures; requires compilation of custom C++/CUDA kernels for optimal memory coalescing.