Sparsity Support Issue 775 Nvidiafastertransformer Github
Sparsity support · Issue #775 · NVIDIA/FasterTransformer · GitHub
Int4 Support · Issue #571 · NVIDIA/FasterTransformer · GitHub
Support for sparse operations · Issue #2735 · NVIDIA/TensorRT · GitHub
INT8 support for GPT-J · Issue #467 · NVIDIA/FasterTransformer · GitHub
It seems not support cudagraph ? · Issue #636 · NVIDIA ...
cuSPARSELt is slower? · Issue #767 · NVIDIA/FasterTransformer · GitHub
Does FT support dynamic shape well? · Issue #579 · NVIDIA ...
How to get started? · Issue #774 · NVIDIA/FasterTransformer · GitHub
2:4 sparsity speedup not expected · Issue #57 · NVIDIA ...
Gaps Between Sparse Support and Support Interface · Issue #6913 ...
Advertisement Space (300x250)
gpu utilization 100% · Issue #189 · NVIDIA/FasterTransformer · GitHub
Support for MSVC on windows ? · Issue #692 · NVIDIA/FasterTransformer ...
FasterTransformer support GPU GeForce RTX 3090? · Issue #90 · NVIDIA ...
GPT latency problem. · Issue #377 · NVIDIA/FasterTransformer · GitHub
Gaps Between Sparse Support and Support Interface · Issue #6913 ...
Support for chatglm-6B/GLM models? · Issue #615 · NVIDIA ...
INT8 Support for GPT models · Issue #265 · NVIDIA/FasterTransformer ...
Does fasttransformer support the m2m100 model？ · Issue #280 · NVIDIA ...
Support model weights and calculations in bfloat16 · Issue #236 ...
Lora Support for Transformer · Issue #641 · NVIDIA/FasterTransformer ...
Advertisement Space (336x280)
Support for Pegasus Models? · Issue #485 · NVIDIA/FasterTransformer ...
Enhancing AI Inference through Sparsity Support and Transformer ...
Should the matrix be set to the following · Issue #199 · NVIDIA ...
GitHub - NVIDIA/TransformerEngine: A library for accelerating ...
Support Seq length up to 8K by zhen-jia · Pull Request #756 · NVIDIA ...
GitHub - BAEK-Parallel-Computing/FasterTransformer-highly-optimized ...
GPT-MoE supports for expert parallel · Issue #743 · NVIDIA ...
Can FasterTransformer support SAM2 ( Meta segment anything model 2 ...
How to serving multi-gpu inference？ · Issue #772 · NVIDIA ...
Benchmark the new PyT data loader (with sparse tensors support ...
Advertisement Space (336x280)
Does it support python api? In a similar way to trtexec, transfer the ...
Does FasterTransformer use FlashAttention? · Issue #758 · NVIDIA ...
Faster Transformer make error · Issue #47 · NVIDIA/FasterTransformer ...
error of 'FasterTransformer.GptOp' · Issue #437 · NVIDIA ...
Does Fused Multi-head Attention support self-defined attention-mask ...
decoupled mode not working when beam_width > 1 · Issue #740 · NVIDIA ...