Ship correct and fast LLM kernels to PyTorch
☆145Jan 14, 2026Updated 2 months ago
Alternatives and similar repositories for BackendBench
Users that are interested in BackendBench are comparing it to the libraries listed below
Sorting:
- Automated GPU Kernel Generation via Co-Evolving Intrinsic World Model☆85Mar 2, 2026Updated 2 weeks ago
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 7 months ago
- A Triton-only attention backend for vLLM☆24Feb 11, 2026Updated last month
- ☆23Jul 11, 2025Updated 8 months ago
- Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.☆84Updated this week
- Automatic differentiation for Triton Kernels☆29Aug 12, 2025Updated 7 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆330Mar 14, 2026Updated last week
- study of cutlass☆22Nov 10, 2024Updated last year
- MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI tr…☆71Updated this week
- extensible collectives library in triton☆97Mar 31, 2025Updated 11 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆97Sep 19, 2025Updated 6 months ago
- ☆13Jan 7, 2025Updated last year
- Debug print operator for cudagraph debugging☆14Aug 2, 2024Updated last year
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆803Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆869Mar 9, 2026Updated last week
- ☆16May 14, 2025Updated 10 months ago
- The tool facilitates debugging convergence issues and testing new algorithms and recipes for training LLMs using Nvidia libraries such as…☆19Sep 17, 2025Updated 6 months ago
- Official Repo of CudaForge☆70Dec 2, 2025Updated 3 months ago
- Ahead of Time (AOT) Triton Math Library☆94Updated this week
- Cataloging released Triton kernels.☆298Sep 9, 2025Updated 6 months ago
- ☆125Updated this week
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- Triton-based Symmetric Memory operators and examples☆91Jan 15, 2026Updated 2 months ago
- Collection of kernels written in Triton language☆184Jan 27, 2026Updated last month
- Code for the 9/6 Hackathon☆56Sep 9, 2025Updated 6 months ago
- Quantized LLM training in pure CUDA/C++.☆241Mar 6, 2026Updated 2 weeks ago
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Jul 21, 2023Updated 2 years ago
- Development containers for triton and triton-cpu☆24Mar 9, 2026Updated last week
- A domain-specific language (DSL) based on Triton but providing higher-level abstractions.☆41Mar 5, 2026Updated 2 weeks ago
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆81Feb 28, 2026Updated 2 weeks ago
- ☆65Apr 26, 2025Updated 10 months ago
- ☆32Apr 19, 2025Updated 11 months ago
- Fast low-bit matmul kernels in Triton☆438Feb 1, 2026Updated last month
- An experimental communicating attention kernel based on DeepEP.☆35Jul 29, 2025Updated 7 months ago
- Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.☆57Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆171Nov 11, 2025Updated 4 months ago
- Code snippets and reproductions from JustAByte☆25Jan 25, 2026Updated last month
- ring-attention experiments☆168Oct 17, 2024Updated last year
- Tile primitives for speedy kernels☆3,232Updated this week