Compare different hardware platforms via the Roofline Model for LLM inference tasks.
☆122Mar 13, 2024Updated 2 years ago
Alternatives and similar repositories for LLMRoofline
Users that are interested in LLMRoofline are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆649Sep 11, 2024Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 4 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆81Aug 12, 2024Updated last year
- A low-latency & high-throughput serving engine for LLMs☆506Jan 8, 2026Updated 5 months ago
- ☆122May 16, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆58May 3, 2026Updated last month
- ☆157Mar 4, 2025Updated last year
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- Handwritten GEMM using Intel AMX (Advanced Matrix Extension)☆17Jan 11, 2025Updated last year
- ☆13Jan 7, 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…☆284Mar 6, 2025Updated last year
- A lightweight design for computation-communication overlap.☆234Jan 20, 2026Updated 4 months ago
- Examples of CUDA implementations by Cutlass CuTe☆278Jul 1, 2025Updated 11 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆672May 21, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Elixir: Train a Large Language Model on a Small GPU Cluster☆16Jun 8, 2023Updated 3 years ago
- A throughput-oriented high-performance serving framework for LLMs☆964Mar 29, 2026Updated 2 months ago
- A CUDA kernel for NHWC GroupNorm for PyTorch☆23Nov 15, 2024Updated last year
- ☆107May 31, 2025Updated last year
- [WIP] Better (FP8) attention for Hopper☆34Feb 24, 2025Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆155May 10, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆304May 1, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,323Aug 28, 2025Updated 9 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆328Jun 10, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆47Jun 11, 2025Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Feb 20, 2026Updated 3 months ago
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆32Mar 7, 2024Updated 2 years ago
- ☆150Jan 9, 2025Updated last year
- High performance Transformer implementation in C++.☆152Jan 18, 2025Updated last year
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆139Feb 22, 2026Updated 3 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,217Updated this week
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆101Apr 20, 2026Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆295Jun 1, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Dynamic Memory Management for Serving LLMs without PagedAttention☆487May 30, 2025Updated last year
- ☆257Oct 24, 2025Updated 7 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆440Mar 5, 2026Updated 3 months ago
- ☆26Feb 17, 2025Updated last year
- A Rust-based Unikernel Enhancing Reliability and Efficiency of Embedded Systems.☆12Jun 28, 2024Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,523Updated this week
- Efficient and easy multi-instance LLM serving☆553Mar 12, 2026Updated 3 months ago