PyRank

Gpu Offloading Python Packages

Python packages with the GitHub topic gpu-offloading. Sorted by monthly downloads, with stars and forks.
pjordanandrsn
experts4bit-qlora

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

16K 3 0
pjordanandrsn
grouped-nf4-gemm

4-bit GPU kernels that compute directly on packed Mixture-of-Experts weights, for training and inference.

12K 2 0
pjordanandrsn
loggetta

Plan and run Mixture-of-Experts fine-tuning on one GPU: check the machine, fit the model, and keep a report of each run.

3K 1 0
pjordanandrsn
e4b

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

143 3 0
pjordanandrsn
experts4bit

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

142 3 0
pjordanandrsn
e4b-qlora

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

140 3 0
pjordanandrsn
experts-mxfp4

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

136 3 0
pjordanandrsn
grouped-mxfp4-gemm

4-bit GPU kernels that compute directly on packed Mixture-of-Experts weights, for training and inference.

87 2 0
pjordanandrsn
expertsnbit

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

82 3 0
pjordanandrsn
gnf4

4-bit GPU kernels that compute directly on packed Mixture-of-Experts weights, for training and inference.

76 2 0
pjordanandrsn
nf4gemm

4-bit GPU kernels that compute directly on packed Mixture-of-Experts weights, for training and inference.

74 2 0