π§± Experimental library for building inference engines
β437Nov 18, 2026Updated this week
Alternatives and similar repositories for resin
Users that are interested in resin are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- β84Updated this week
- β201Nov 10, 2026Updated last week
- [Tech Report] On the Design of Hyper-Connections: Simplification, Stability, and Scalability. The fastest Hyper-Connections method with cβ¦β21Nov 8, 2026Updated last week
- reproducing the flapping airplanes megakernel, in collab with magniβ142Nov 8, 2026Updated last week
- Own your Tinker-compatible training stackβ45Updated this week
- Managed Kubernetes at scale on DigitalOcean β’ AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- TokenSpeed is a speed-of-light LLM inference engine.β2,934Updated this week
- Code for the paper ReplaySSM: Cache SSM Inputs, Not Stateβ75Oct 13, 2026Updated last month
- Auto researching harness that burns through everything.β107Updated this week
- Jev-compatible API endpoint based on open models (prefill-only)β334Oct 1, 2026Updated last month
- Programmable chat templates for LLM training and inference.β171Updated this week
- β473Updated this week
- Mixture-of-experts (MoE) training megakernel for NVL72sβ647Oct 1, 2026Updated last month
- MoE training for Me and You and maybe other peopleβ400Mar 15, 2026Updated 8 months ago
- RL a search agent on SEC filings with Tinker (Dr. GRPO, gpt-oss-20b)β24Sep 17, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer β’ AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- β107Oct 25, 2026Updated 3 weeks ago
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flintβ¦β44Nov 4, 2026Updated 2 weeks ago
- Local autoresearch on a MacBook, with Flint: geometry, scheduling and machine learning experiments.β111Oct 27, 2026Updated 3 weeks ago
- TEVO: evolve LM motifs cheaply, then validate them in downstream train.py loops.β20Apr 18, 2026Updated 7 months ago
- JAX in JavaScript β ML library for the web, running on WebGPU & Wasmβ953Updated this week
- Stitch your rollouts together across clouds and regionsβ40Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.β3,331Updated this week
- A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorchβ387Jul 9, 2026Updated 4 months ago
- A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.β4,374Oct 17, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decodingβ206Updated this week
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.β14Oct 30, 2026Updated 2 weeks ago
- Winner π (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an averageβ¦β319Sep 12, 2026Updated 2 months ago
- β41Aug 16, 2026Updated 3 months ago
- PorTAL generates portable task specific LoRA adapters that can efficiently transfer across language models.β129Jul 27, 2026Updated 3 months ago
- Reference implementation and examples of the CuTe Layout representation and algebra.β397Nov 3, 2026Updated 2 weeks ago
- Virtual filesystem overlay built on event streams for state replay and time travelβ210Oct 23, 2026Updated 3 weeks ago
- β11Oct 29, 2026Updated 2 weeks ago
- Neural networks trained in Bend 2: typed forward/backward layers, laws checked by the kernel, agreement with PyTorchβ19Updated this week
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An agent runtime and tool protocol for principled agent concurrencyβ834Nov 9, 2026Updated last week
- Fastest concurrent ordered mapβ668Updated this week
- Halo is an open-source framework built by White Circle for training large language and multimodal modelsβ862Updated this week
- A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.β259Jun 29, 2026Updated 4 months ago
- Tile primitives for speedy kernelsβ3,803Sep 12, 2026Updated 2 months ago
- Ship correct and fast LLM kernels to PyTorchβ156Jan 14, 2026Updated 10 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IPβ165Sep 12, 2025Updated last year
Are these results useful?