A small, readable PyTorch inference engine for Qwen3-4B with continuous batching, native paged attention, prefix caching, and an OpenAI-compatible chat completions API.
☆18Oct 24, 2026Updated 2 weeks ago
Alternatives and similar repositories for helios
Users that are interested in helios are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Curated Collection of Frontier Language Model Architectures☆14Jan 30, 2026Updated 9 months ago
- ☆12Aug 25, 2026Updated 2 months ago
- Protocol-layer firewall that intercepts PostgreSQL wire messages & block destructive SQL patterns before reaching any instance.14-15 ms p…☆12Jun 25, 2026Updated 4 months ago
- ☆11May 16, 2025Updated last year
- A hardware hybrid scheduling tensor engine. Improves performace by 35% for medium workload compared to pure GPU.☆13Jun 22, 2026Updated 4 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- a guide to learn and implement inference techniques from scratch☆14Jun 18, 2026Updated 4 months ago
- event-sourced adk for go☆12May 7, 2026Updated 6 months ago
- Event processing engine built in go☆12Sep 27, 2026Updated last month
- ☆14Aug 1, 2026Updated 3 months ago
- ☆13Jul 12, 2026Updated 3 months ago
- miniature Linux container runtime in C++ built to understand containers from first principles.☆23Jul 25, 2026Updated 3 months ago
- A curated resource list for learning post training☆22Oct 11, 2026Updated last month
- Transformer-ConvNet with Masked AutoEncoder for Cardiac Image Registration☆11Aug 29, 2022Updated 4 years ago
- The fastest inference framework to run AI on CPUs☆20Jun 12, 2026Updated 5 months ago
- 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.
- Programmable automated machine learning - proof of concept☆15Oct 9, 2024Updated 2 years ago
- A practical series for developers who want to move beyond writing code and start designing systems. Learn mental models for abstraction, …☆21May 20, 2026Updated 5 months ago
- ☆26Jul 17, 2026Updated 3 months ago
- A tiny macOS menu bar app that turns your CPU load into a sprinting animal 🐾☆20Jun 21, 2026Updated 4 months ago
- GitLogs — auto-tweets GitHub commits with Gemini. Deterministic Commit Intelligence layer + 30-commit golden eval at P/R/F1/acc = 1.00. L…☆22Jul 27, 2026Updated 3 months ago
- everything you need to know about inference engineering☆45Sep 29, 2026Updated last month
- Redis-compatible in-memory key-value server in Rust with RESP2, AOF persistence, recovery, and configurable durability (fsync) policies.☆19Mar 10, 2026Updated 8 months ago
- Course on Flash-attention in Triton☆103Feb 9, 2026Updated 9 months ago
- A repository for awesome resources in mechanistic interpretability☆17Jan 18, 2023Updated 3 years 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 distributed OLTP database, built using Rust.☆23Sep 28, 2026Updated last month
- A distributed training framework based on torchtitan☆110Aug 17, 2026Updated 2 months ago
- autonomous flash-loan arbitrage engine on arbitrum. made in rust + solidity☆26Mar 23, 2026Updated 7 months ago
- 初学者脚本，用来查询自己是不是在已经泄露的华住会数据中☆12Aug 29, 2018Updated 8 years ago
- ☆13Jan 3, 2020Updated 6 years ago
- Kubernetes API client examples in Go☆11Apr 19, 2019Updated 7 years ago
- git-operator provides a REST-based interface for submitting Kustomize based resources as pull-requests into Git repos. It enables integra…☆13Jun 14, 2023Updated 3 years ago
- Repository containing ULX3S blink LED binaries☆16May 16, 2022Updated 4 years ago
- Bitwise-identical token probabilities between RL rollout (vLLM) and training☆40Updated 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.
- A Base32-Crockford encoded API Key generator, validator and converter to turn UUIDs into human readable API Keys for Golang☆10Dec 6, 2018Updated 7 years ago
- Display your Spotify listening status on GH README and websites with a beautiful, customizable widget.☆29Dec 23, 2025Updated 10 months ago
- A weekly updated awesome list of RL, RLHF, DPO, GRPO, reward models, and preference optimization for image and video diffusion generation…☆18Oct 19, 2026Updated 3 weeks ago
- Transformer + GAT for RNA chemical reactivity prediction| Stanford Ribonanza☆11Jan 28, 2026Updated 9 months ago
- SipHash AVX2 implementation in C☆16Mar 3, 2016Updated 10 years ago
- GPT with metaweights: weights that don't actually exist☆26Oct 4, 2026Updated last month
- A cache-aware, tensor-optimized memory allocator in C++☆29Apr 27, 2026Updated 6 months ago
Are these results useful?