Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
☆705Sep 18, 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…☆207Updated this week
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 8 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,146Updated this week
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆60Feb 6, 2026Updated 7 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,780Aug 13, 2026Updated last month
- 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.
- Early-stage Rust drop-in alternative frontend for vLLM☆73May 22, 2026Updated 3 months ago
- High-performance Rust benchmark client for vLLM serving endpoints.☆52Aug 3, 2026Updated last month
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,606Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,093May 17, 2026Updated 4 months ago
- Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.☆322Sep 9, 2026Updated last week
- Learning TileLang with 10 puzzles!☆380Aug 11, 2026Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,431Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆276Updated this week
- High Performance LLM Inference Operator Library☆1,160Sep 7, 2026Updated last 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.
- FlashInfer: Kernel Library for LLM Serving☆6,443Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,254Sep 1, 2026Updated 2 weeks ago
- ☆117Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 7 months ago
- ☆856Updated this week
- FLA but cuTile☆27Apr 17, 2026Updated 5 months ago
- ☆456Aug 26, 2026Updated 3 weeks ago
- Distributed Compiler and Optimized Parallel Kernels☆1,546Updated this week
- Nano vLLM☆15,505Apr 26, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,044Updated this week
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆297Updated this week
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 6 months ago
- LLM Inference FrameWork☆38May 20, 2026Updated 3 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆8,114Updated this week
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,227Updated 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…☆974Updated this week
- KV cache store for distributed LLM inference☆439Updated this week
- My learning notes for ML SYS.☆7,369Sep 10, 2026Updated last week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,577Updated this week
- From Minimal GEMM to Everything☆243Jul 9, 2026Updated 2 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆147Jul 9, 2026Updated 2 months ago
- Open sources book with Modern CUDA Learn Notes for Beginners, includes FP16/BF16, FP8, HGEMM, FlashAttention, CuTe, etc.☆11,979Updated this week
- Skills for writing tilelang and debugging with CUDA toolkits.☆143Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,503Sep 12, 2026Updated last week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆547Sep 8, 2026Updated last week