IBM / triton-dejavu
Framework to reduce autotune overhead to zero for well known deployments.
☆63Updated this week
Alternatives and similar repositories for triton-dejavu:
Users that are interested in triton-dejavu are comparing it to the libraries listed below
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing. By pro…☆68Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆104Updated this week
- GPTQ inference TVM kernel☆39Updated 10 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆74Updated 4 months ago
- ☆26Updated this week
- Quantized Attention on GPU☆45Updated 4 months ago
- ☆73Updated 4 months ago
- ☆19Updated 5 months ago
- extensible collectives library in triton☆84Updated 6 months ago
- Transformers components but in Triton☆32Updated this week
- ☆87Updated 6 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆70Updated 6 months ago
- ☆64Updated 2 months ago
- Implement Flash Attention using Cute.☆71Updated 3 months ago
- ☆46Updated 2 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆59Updated 2 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆100Updated 8 months ago
- Benchmark tests supporting the TiledCUDA library.☆15Updated 4 months ago
- ☆74Updated 3 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆106Updated 6 months ago
- ☆62Updated 3 weeks ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆85Updated 6 years ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆35Updated 2 weeks ago
- ☆101Updated 6 months ago
- llama INT4 cuda inference with AWQ☆53Updated 2 months ago
- ☆55Updated 2 months ago