Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
☆726Oct 26, 2026Updated this week
Alternatives and similar repositories for pegainfer
Users that are interested in pegainfer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆218Updated this week
- A model-agnostic GPU runtime for shipping models as verified programs.☆145Updated this week
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 9 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,820Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,875Sep 24, 2026Updated last month
- 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.
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 8 months ago
- Early-stage Rust drop-in alternative frontend for vLLM☆73May 22, 2026Updated 5 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,911Updated this week
- ☆134Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,483Oct 19, 2026Updated last week
- Learning TileLang with 10 puzzles!☆392Aug 11, 2026Updated 2 months ago
- High-performance Rust benchmark client for vLLM serving endpoints.☆52Aug 3, 2026Updated 2 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,471May 17, 2026Updated 5 months ago
- Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.☆344Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- FlashInfer: Kernel Library for LLM Serving☆6,806Updated this week
- High Performance LLM Inference Operator Library☆1,185Sep 7, 2026Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,845Updated this week
- High Performance Serving Runtime For Interactive Super Intelligence System☆1,650Updated this week
- ☆1,081Updated this week
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆442Updated this week
- High-performance LLM operator library built on TileLang.☆202Updated this week
- Nano vLLM☆16,211Apr 26, 2026Updated 6 months ago
- A tutorial on modern GPU programming for machine learning systems☆1,372Updated this 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.
- A Datacenter Scale Distributed Inference Serving Framework☆8,409Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,576Sep 18, 2026Updated last month
- My learning notes for ML SYS.☆7,617Oct 21, 2026Updated last week
- A from-scratch Prefill/Decode disaggregation inference engine for LLMs☆163May 10, 2026Updated 5 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆306Oct 17, 2026Updated last week
- ☆306Sep 5, 2026Updated last month
- Fairy☆22Aug 23, 2026Updated 2 months ago
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,790Oct 22, 2026Updated last week
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆13Oct 20, 2026Updated last week
- 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.
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,380Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,582Updated this week
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆17May 25, 2026Updated 5 months ago
- OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one G…☆48Sep 30, 2026Updated 3 weeks ago
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,135Updated this week
- how to optimize some algorithm in cuda.☆3,335Oct 11, 2026Updated 2 weeks ago
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago