Compare different hardware platforms via the Roofline Model for LLM inference tasks.
☆120Mar 13, 2024Updated last year
Alternatives and similar repositories for LLMRoofline
Users that are interested in LLMRoofline are comparing it to the libraries listed below
Sorting:
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆619Sep 11, 2024Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆27Jan 22, 2026Updated last month
- ☆13Jan 7, 2025Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆79Aug 12, 2024Updated last year
- ☆115May 16, 2025Updated 9 months ago
- A low-latency & high-throughput serving engine for LLMs☆480Jan 8, 2026Updated last month
- ☆88May 31, 2025Updated 9 months ago
- ☆155Mar 4, 2025Updated 11 months ago
- Examples of CUDA implementations by Cutlass CuTe☆269Jul 1, 2025Updated 8 months ago
- A lightweight design for computation-communication overlap.☆223Jan 20, 2026Updated last month
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆644Jan 15, 2026Updated last month
- Handwritten GEMM using Intel AMX (Advanced Matrix Extension)☆17Jan 11, 2025Updated last year
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆282Mar 6, 2025Updated 11 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆147May 10, 2025Updated 9 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆57Jul 23, 2024Updated last year
- A CUDA kernel for NHWC GroupNorm for PyTorch☆23Nov 15, 2024Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆46Jun 11, 2025Updated 8 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Feb 20, 2026Updated last week
- Elixir: Train a Large Language Model on a Small GPU Cluster☆15Jun 8, 2023Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆946Oct 29, 2025Updated 4 months ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆124Feb 22, 2026Updated last week
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- A Rust-based Unikernel Enhancing Reliability and Efficiency of Embedded Systems.☆11Jun 28, 2024Updated last year
- ☆20Dec 24, 2024Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆283May 1, 2025Updated 10 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,261Aug 28, 2025Updated 6 months ago
- [WIP] Better (FP8) attention for Hopper☆32Feb 24, 2025Updated last year
- ☆152Jan 9, 2025Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆314Jun 10, 2025Updated 8 months ago
- Kernel Library Wheel for SGLang☆16Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆488Jan 20, 2026Updated last month
- Implement Flash Attention using Cute.☆101Dec 17, 2024Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆288Jun 5, 2024Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆410Feb 11, 2026Updated 2 weeks ago
- ☆261Jul 11, 2024Updated last year
- ☆26Feb 17, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆464May 30, 2025Updated 9 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆55Jan 12, 2026Updated last month
- learning how CUDA works☆377Mar 3, 2025Updated last year