ROCm / TransformerEngine
☆13Updated this week
Related projects ⓘ
Alternatives and complementary repositories for TransformerEngine
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- ☆49Updated 2 weeks ago
- ☆55Updated 6 months ago
- extensible collectives library in triton☆72Updated 2 months ago
- ☆50Updated this week
- Simple and fast low-bit matmul kernels in CUDA / Triton☆147Updated this week
- ☆47Updated 2 months ago
- Development repository for the Triton language and compiler☆96Updated this week
- ☆12Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago
- Ahead of Time (AOT) Triton Math Library☆41Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆211Updated 3 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆98Updated 2 months ago
- ☆90Updated 2 months ago
- RCCL Performance Benchmark Tests☆51Updated last month
- An extension library of WMMA API (Tensor Core API)☆84Updated 4 months ago
- Fast and memory-efficient exact attention☆30Updated last month
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆181Updated last year
- llama INT4 cuda inference with AWQ☆48Updated 4 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- ☆169Updated 4 months ago
- ☆33Updated 2 months ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.