dlsyscourse / lecture14
☆9Updated 11 months ago
Related projects: ⓘ
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆20Updated 5 months ago
- GPTQ inference TVM kernel☆35Updated 4 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆93Updated last week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆82Updated 6 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆50Updated 3 months ago
- llama INT4 cuda inference with AWQ☆46Updated 2 months ago
- ☆50Updated 3 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆20Updated last week
- ☆17Updated this week
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 3 years ago
- ☆66Updated last year
- study of cutlass☆18Updated last year
- ☆67Updated last week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆81Updated 2 months ago
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆129Updated last year
- CUDA 12.2 HMM demos☆16Updated last month
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆61Updated 2 years ago
- ☆16Updated this week
- benchmarking some transformer deployments☆26Updated last year
- Benchmark code for the "Online normalizer calculation for softmax" paper☆52Updated 6 years ago
- ☆48Updated 6 months ago
- Benchmark scripts for TVM☆73Updated 2 years ago
- ☆52Updated this week
- Memory Optimizations for Deep Learning (ICML 2023)☆58Updated 6 months ago
- ☆22Updated 4 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆41Updated 3 weeks ago
- play gemm with tvm☆81Updated last year
- Distributed DataLoader For Pytorch Based On Ray☆24Updated 2 years ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆118Updated last year
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆40Updated last week