NVIDIA Inference Benchmarks provide recipes in ready-to-use templates for evaluating platform speed. Validate your platform across specific AI use cases across hardware and software combinations.
☆40Aug 3, 2026Updated this week
Alternatives and similar repositories for srt-slurm
Users that are interested in srt-slurm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Benchmark SGLang on SLURM☆24Apr 20, 2026Updated 3 months ago
- Empowering LLM Agents for Real-World Computer System Optimization☆17Sep 10, 2025Updated 10 months ago
- Dashboard for InferenceX™, Open Source Continuous Inference☆37Updated this week
- ☆13Jun 18, 2024Updated 2 years ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆34Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆317Updated this week
- ☆28Jul 29, 2025Updated last year
- AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solu…☆499Updated this week
- Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200…☆1,313Updated this week
- A Top-Down Profiler for GPU Applications☆23Feb 29, 2024Updated 2 years ago
- ☆68Updated this week
- ☆125May 10, 2026Updated 2 months ago
- Incubating P/D sidecar for llm-d☆17Nov 13, 2025Updated 8 months ago
- Recipes for reproducing training and serving benchmarks for large machine learning models using GPUs on Google Cloud.☆139Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node☆72May 16, 2026Updated 2 months ago
- Estimate MFU for DeepSeekV3☆26Jan 5, 2025Updated last year
- NVIDIA NCCL Tests for Distributed Training☆152Updated this week
- ☆333Updated this week
- A unified VLA post-training framework for human-in-the-loop data collection, fine-tuning, and reinforcement learning.☆45Updated this week
- ☆22May 5, 2025Updated last year
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆105Updated this week
- ☆65Apr 26, 2025Updated last year
- ☆22Mar 11, 2026Updated 4 months 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.
- common NVCF components☆15May 5, 2026Updated 2 months ago
- torchvision-based transforms that provide access to parameterization☆13Dec 4, 2025Updated 7 months ago
- JAX bindings for the flash-attention3 kernels☆23Jan 2, 2026Updated 7 months ago
- High-performance Rust benchmark client for vLLM serving endpoints.☆51Updated this week
- A high-performance and light-weight router for vLLM large scale deployment☆341Jul 24, 2026Updated last week
- TensorRT encapsulation, learn, rewrite, practice.☆31Oct 19, 2022Updated 3 years ago
- A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.☆19Jul 28, 2026Updated last week
- Benchmarking Open-Ended Inference Optimization by AI Agents☆34Jul 6, 2026Updated 3 weeks ago
- Frontier: A Discrete-Event Simulator for Modern LLM Serving☆77Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆72Mar 17, 2026Updated 4 months ago
- Nano SGLang☆16Jul 21, 2025Updated last year
- Compare Bloxroute and Fiber transaction streams☆10Nov 22, 2024Updated last year
- Proof of concept implementation of Sigmabus https://eprint.iacr.org/2023/1406☆10Dec 20, 2023Updated 2 years ago
- A test library for computing modular exponentiation in parallel using AVX-512 vector arithmetic☆12Dec 18, 2023Updated 2 years ago
- CDLS: Proving Knowledge of Committed Discrete Logarithms with Soundness☆12Apr 30, 2026Updated 3 months ago
- Hypercorn is an ASGI and WSGI Server based on Hyper libraries and inspired by Gunicorn.☆21Jan 12, 2026Updated 6 months ago