Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
☆628Aug 5, 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…☆184Updated this week
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 6 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆1,804Updated this week
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 5 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,621Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Early-stage Rust drop-in alternative frontend for vLLM☆73May 22, 2026Updated 2 months ago
- High-performance Rust benchmark client for vLLM serving endpoints.☆51Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,172Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,684May 17, 2026Updated 2 months ago
- Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.☆299Updated this week
- Learning TileLang with 10 puzzles!☆362May 28, 2026Updated 2 months ago
- ☆60Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆263Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,130Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- High Performance LLM Inference Operator Library☆1,085Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,165Jul 30, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,106Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 6 months ago
- ☆717Updated this week
- ☆352Jun 9, 2026Updated last month
- ☆806Jun 2, 2026Updated 2 months ago
- FLA but cuTile☆27Apr 17, 2026Updated 3 months ago
- Nano vLLM☆14,833Apr 26, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆220Updated this week
- SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models☆746Updated this week
- Some funny cute/cuteDSL code snippets☆33Mar 2, 2026Updated 5 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,507Jul 20, 2026Updated 2 weeks ago
- LLM Inference FrameWork☆31May 20, 2026Updated 2 months ago
- KV cache store for distributed LLM inference☆424Nov 13, 2025Updated 8 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,686Updated this week
- cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for pa…☆727Updated this week
- From Minimal GEMM to Everything☆232Jul 9, 2026Updated 3 weeks ago
- 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.
- A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.☆4,442Updated this week
- My learning notes for ML SYS.☆6,825Updated this week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆140Jul 9, 2026Updated 3 weeks ago
- ☆240Jul 29, 2026Updated last week
- ☆312Updated this week
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,710Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,296Updated this week