Pinned Loading
-
facebookresearch/LayerSkip
facebookresearch/LayerSkip PublicCode for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
-
facebookresearch/any4
facebookresearch/any4 PublicQuantize transformers to any learned arbitrary 4-bit numeric format
-
facebookresearch/MODel_opt
facebookresearch/MODel_opt Public archiveMemory Optimizations for Deep Learning (ICML 2023)
-
meta-pytorch/superblock
meta-pytorch/superblock Public archiveA block oriented training approach for inference time optimization.
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.