Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature set.
☆130Aug 29, 2026Updated this week
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 Ascend☆2,736Updated this week
- SGLang kernel library for NPU☆174Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,221Updated this week
- LMCache-Ascend is a plugin for running LMCache on the Ascend NPU.☆87Updated this week
- [ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"☆31Jun 1, 2026Updated 3 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.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,446Updated this week
- Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extensio…☆25May 5, 2026Updated 3 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…☆1,544Updated this week
- AISBench Benchmark is a model evaluation tool built on OpenCompass, compatible with OpenCompass’s configuration system, dataset structure…☆423Updated this week
- ☆11Jan 26, 2022Updated 4 years ago
- ☆549Updated this week
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Jun 5, 2026Updated 2 months ago
- KV cache store for distributed LLM inference☆433Nov 13, 2025Updated 9 months ago
- ☆27Jun 8, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A Triton JIT runtime and ffi provider in C++☆40Aug 7, 2026Updated 3 weeks ago
- ☆28Updated this week
- Visualize the Expert Parallelism Load Balancer☆19Mar 15, 2025Updated last year
- ☆26Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆131Dec 25, 2025Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,298Updated this week
- The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.☆292Sep 26, 2025Updated 11 months ago
- A benchmarking tool for comparing different LLM API providers' DeepSeek model deployments.☆31Mar 28, 2025Updated last year
- The code based on vLLM for the paper “ Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention”.☆11Sep 19, 2024Updated last year
- 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 workload for deploying LLM inference services on Kubernetes☆289Updated this week
- This project contains code for the paper titled "SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentia…☆29Feb 21, 2024Updated 2 years ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,928Updated this week
- A CUDA kernel for NHWC GroupNorm for PyTorch☆26Nov 15, 2024Updated last year
- ☆56Jul 7, 2025Updated last year
- A collection of optimal and heuristic scheduling tools☆17Apr 24, 2026Updated 4 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,310Updated this week
- ☆59May 20, 2026Updated 3 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆467Updated 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.
- ☆163Mar 5, 2026Updated 5 months ago
- A high-performance and light-weight router for vLLM large scale deployment☆385Updated this week
- ☆74Updated this week
- GMM model for subtracting background from foreground☆10Nov 10, 2020Updated 5 years ago
- Offline optimization of your disaggregated Dynamo graph☆430Updated this week
- Universal data IO and neural network modules in NLP tasks.☆18Apr 13, 2026Updated 4 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆375Jan 30, 2026Updated 7 months ago