thuml / learn_torch.compileLinks
torch.compile artifacts for common deep learning models, can be used as a learning resource for torch.compile
☆18Updated last year
Alternatives and similar repositories for learn_torch.compile
Users that are interested in learn_torch.compile are comparing it to the libraries listed below
Sorting:
- Quantized Attention on GPU☆44Updated 11 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆85Updated last month
- ☆106Updated 5 months ago
- ☆50Updated 5 months ago
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆17Updated 11 months ago
- ☆120Updated 2 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 4 months ago
- ☆56Updated last week
- ☆23Updated 6 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 11 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆21Updated 3 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- DeeperGEMM: crazy optimized version☆73Updated 6 months ago
- GPTQ inference TVM kernel☆39Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆51Updated last year
- ☆31Updated 4 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆93Updated 9 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆124Updated 6 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- A Triton JIT runtime and ffi provider in C++☆29Updated last week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 4 months ago
- Quantize transformers to any learned arbitrary 4-bit numeric format☆49Updated 4 months ago
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆25Updated this week
- ☆65Updated 6 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Updated last year
- ☆77Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 5 months ago
- Simple python library for generating your own perfetto traces for your application. Can be used for both app instrumentation and custom …☆20Updated 4 months ago
- ☆71Updated 7 months ago