Pipeline-parallel LLM inference across GPUs on separate machines.
☆458Aug 9, 2026Updated last month
Alternatives and similar repositories for shard
Users that are interested in shard are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Uncensored, private, decentralized AI inference on Solana.☆75Updated this week
- Full Transformer into a custom chip. microGPT in RTL, generating names on a Virtex-5 FPGA at ~56k tokens/second.☆651Jun 25, 2026Updated 3 months ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,901Updated this week
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 4 months ago
- NVFP4 Gemma-4 26B-A4B MoE for DGX Spark — optimal recipe: DFlash n=10 (flex) on AEON vLLM Ultimate. 144 tok/s single / 1,724 peak (Coding…☆44Updated 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.
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆40Jul 9, 2026Updated 2 months ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,358Updated this week
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆541Updated this week
- Mixed-vendor GPU inference cluster manager with speculative decoding☆37Jul 2, 2026Updated 3 months ago
- A private, open-source alternative to Windows Recall — for Linux. Captures your screen, OCRs it, and makes everything you've seen instant…☆55Sep 22, 2026Updated 2 weeks ago
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆23,698Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,821Updated this week
- AI Agents designed to help manage and update EventCatalog for users☆40Jul 7, 2026Updated 3 months ago
- An arbitrage bot is a smart contract connected to an external automation script that controls its operation.☆2,789Updated 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.
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated last week
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Nov 11, 2024Updated last year
- Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside emb…☆48Updated this week
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated last month
- Bonsai Demo☆3,300Updated this week
- Production-grade DSPy 3.2.x agent skills + validated end-to-end examples for Claude Code and Codex CLI — fundamentals, evaluation, GEPA, …☆278Sep 6, 2026Updated last month
- A CLI tool for managing GitHub Actions workflows☆15Jan 3, 2026Updated 9 months ago
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆232Sep 27, 2026Updated last week
- ☆19Mar 21, 2026Updated 6 months ago
- 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.
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆27Jul 8, 2026Updated 3 months ago
- ☆53Updated this week
- Interactive live visualizer for gepa runs☆423May 26, 2026Updated 4 months ago
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆34Jul 12, 2026Updated 2 months ago
- KalamDB — a lightweight, real-time, storage-efficient SQL database. Designed for per-user data isolation and scalable performance — ideal…☆53Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,197Jul 9, 2026Updated 2 months ago
- top, but for the HTTP endpoints on your host — a live dashboard of the most active plaintext HTTP endpoints, right in the terminal.☆225Sep 23, 2026Updated 2 weeks ago
- ☆39Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,143Aug 18, 2026Updated last month
- 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.
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆30Jul 8, 2026Updated 3 months ago
- Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere☆1,397Jul 1, 2026Updated 3 months ago
- Adaptive Test-time Learning and Autonomous Specialization☆2,098Updated this week
- Browser System With Zero HTML/CSS/JS☆30Aug 28, 2026Updated last month
- OpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime☆303Jul 2, 2026Updated 3 months ago
- Usage indicator extension for pi with footer status bars and /usage command☆14Apr 17, 2026Updated 5 months ago
- KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. …☆508Jun 22, 2026Updated 3 months ago