Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature set.
☆131Sep 20, 2026Updated 3 weeks ago
Alternatives and similar repositories for omni-infer
Users that are interested in omni-infer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Community maintained hardware plugin for vLLM on Huawei Ascend☆2,949Updated this week
- SGLang kernel library for NPU☆192Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,295Updated this week
- LMCache-Ascend is a plugin for running LMCache on the Ascend NPU.☆90Sep 29, 2026Updated 2 weeks ago
- [ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"☆32Sep 21, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,773Updated this week
- Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extensio…☆27May 5, 2026Updated 5 months ago
- A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Fou…☆1,595Updated this week
- ☆11Jan 26, 2022Updated 4 years ago
- ☆549Aug 27, 2026Updated last month
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Updated this week
- Triton language and compiler for Ascend NPU☆186Updated this week
- KV cache store for distributed LLM inference☆446Sep 16, 2026Updated 3 weeks ago
- ☆28Jun 8, 2026Updated 4 months ago
- 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 Triton JIT runtime and ffi provider in C++☆41Sep 24, 2026Updated 2 weeks ago
- Visualize the Expert Parallelism Load Balancer☆17Mar 15, 2025Updated last year
- AISBench Benchmark is a model evaluation tool built on OpenCompass, compatible with OpenCompass’s configuration system, dataset structure…☆789Updated this week
- ☆27Sep 30, 2026Updated last week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆136Dec 25, 2025Updated 9 months ago
- ☆31Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,594Updated this week
- The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.☆293Sep 26, 2025Updated last year
- A Datacenter Scale Distributed Inference Serving Framework☆8,257Updated this week
- 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.
- The code based on vLLM for the paper “ Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention”.☆11Sep 19, 2024Updated 2 years ago
- A benchmarking tool for comparing different LLM API providers' DeepSeek model deployments.☆31Mar 28, 2025Updated last year
- A workload for deploying LLM inference services on Kubernetes☆303Updated this week
- A CUDA kernel for NHWC GroupNorm for PyTorch☆26Nov 15, 2024Updated last year
- ☆57Jul 7, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆16Jul 19, 2026Updated 2 months ago
- ☆60May 20, 2026Updated 4 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,583Updated this week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆488Sep 23, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆170Mar 5, 2026Updated 7 months ago
- This repository contains the artifact for the SOSP'23 paper: Sishuai Gong, Dinglan Peng, Deniz Altınbüken, Pedro Fonseca, Petros Maniati…☆17Oct 24, 2023Updated 2 years ago
- ☆74Sep 22, 2026Updated 3 weeks ago
- A high-performance and light-weight router for vLLM large scale deployment☆467Updated this week
- GMM model for subtracting background from foreground☆10Nov 10, 2020Updated 5 years ago
- Universal data IO and neural network modules in NLP tasks.☆18Apr 13, 2026Updated 6 months ago
- Offline optimization of your disaggregated Dynamo graph☆458Sep 18, 2026Updated 3 weeks ago