yinuotxie / Efficient-LLM-Inferencing-on-GPUsLinks
Penn CIS 5650 (GPU Programming and Architecture) Final Project
☆39Updated last year
Alternatives and similar repositories for Efficient-LLM-Inferencing-on-GPUs
Users that are interested in Efficient-LLM-Inferencing-on-GPUs are comparing it to the libraries listed below
Sorting:
- ☆98Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last week
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 6 months ago
- llama INT4 cuda inference with AWQ☆54Updated 8 months ago
- ☆104Updated 4 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆112Updated 4 months ago
- A practical way of learning Swizzle☆27Updated 7 months ago
- play gemm with tvm☆91Updated 2 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆65Updated last year
- Optimize GEMM with tensorcore step by step☆32Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆220Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆75Updated last year
- ☆150Updated 8 months ago
- study of Ampere' Sparse Matmul☆18Updated 4 years ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆59Updated 3 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆57Updated 5 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆71Updated last week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆108Updated 4 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆106Updated 2 months ago
- Implement Flash Attention using Cute.☆95Updated 9 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated last year
- ☆85Updated 5 months ago
- ☆108Updated 5 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆43Updated 3 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆185Updated 7 months ago
- FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.☆85Updated this week
- hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.☆50Updated 2 years ago
- ☆42Updated last year
- A lightweight design for computation-communication overlap.☆167Updated last week
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆53Updated last year