DeepSeek-V3/R1 inference performance simulator
☆199Mar 27, 2025Updated last year
Alternatives and similar repositories for shallowsim
Users that are interested in shallowsim are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆99Apr 2, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- ☆32Jul 2, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,375Aug 28, 2025Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Distributed Compiler and Optimized Parallel Kernels☆1,576Sep 18, 2026Updated last month
- ☆44Oct 12, 2025Updated last year
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Analyze computation-communication overlap in V3/R1.☆1,202Mar 21, 2025Updated last year
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- ☆391Jan 28, 2026Updated 9 months ago
- Perplexity GPU Kernels☆614Nov 7, 2025Updated 11 months ago
- ☆54May 19, 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.
- FLA but cuTile☆27Apr 17, 2026Updated 6 months ago
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆719Aug 24, 2026Updated 2 months ago
- Tile-based language built for AI computation across all scales☆196Aug 25, 2026Updated 2 months ago
- ☆1,230Sep 20, 2026Updated last month
- ☆46Oct 15, 2025Updated last year
- Unified tracing profiler and visualizer, one timeline from CPU to GPU/HES to in-kernel zones☆150Sep 21, 2026Updated last month
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- a static analytical model for LLM distributed training☆177May 11, 2026Updated 5 months ago
- ☆65Apr 26, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale☆719Updated this week
- ☆37Aug 7, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- ☆295Oct 24, 2025Updated last year
- Composable and Embeddable Communication Runtime for Distributed AI Services☆102Oct 7, 2026Updated 3 weeks ago
- ☆138Updated this week
- ☆68Feb 24, 2026Updated 8 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆689Sep 11, 2024Updated 2 years ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆119Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆103Jan 16, 2026Updated 9 months ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆122Dec 17, 2025Updated 10 months ago
- ☆98Feb 5, 2026Updated 8 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- High-performance LLM operator library built on TileLang.☆202Updated this week