NVIDIA/FasterTransformer Issues
what is the mean of EFF-FT?
Updatedcore dumped of swin model
Updated 1Sparsity support
UpdatedHow to get started?
Updated[Long seq length] GPT Seq length constrain
Updated 14TP=2, Loss of accuracy
Updated 2cuSPARSELt is slower?
Updated 1Compatibility issue with CUDA 12.2
Updated 5Limit cuda memory growth
Updated