Search: github.com/gpujs | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

241.

Show HN: Made a batching LLM API for a project. Mistral 200 tk/s on RTX 3090 (github.com/epolewski)

3 points

2 years ago

242.

Apple predicted the rise of local LLMs, hence the M2 Ultra

2 points

3 years ago

243.

Show HN: Trained a 12M transformer on an ML framework we built from scratch (github.com/mni-ml)

2 points

2 months ago

244.

A 100% serverless RAG that extracts complex tables better than NotebookLM

2 points

2 months ago

245.

Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU (github.com/yousef-rafat)

2 points

3 months ago

246.

Show HN: I built a unified inference layer for Document Processing Models (github.com/adithya-s-k)

2 points

3 months ago

247.

Show HN: FT-Lab – Lightweight TinyLlama Fine-Tuning (Full FT / LoRA / QLoRA) (github.com/REICHIYAN)

2 points

6 months ago

248.

Show HN: SimMS – GPU accelerated mass spectra search (github.com/PangeAI)

2 points

a year ago

249.

Show HN: node-mlx – Machine learning framework for Node.js (github.com/frost-beta)

2 points

2 years ago

250.

Show HN: Supamodel -- monitor ML training sessions on your iPhone (supamodel.ai)

2 points

2 years ago

251.

Show HN: I built vector search for COSS podcasts & livestreams (tv.algora.io)

2 points

2 years ago

252.

Show HN: SenseThing, sensor logging and remote monitoring for Linux (github.com/ryukoposting)

2 points

2 years ago

253.

Show HN: Ditty – Simple Finetuning (github.com/iantbutler01)

2 points

3 years ago

254.

Show HN: Nos – Open-Source to Maximize GPU Utilization in Kubernetes (github.com/nebuly-ai)

2 points

3 years ago

255.

Docker files for building ROS Kinetic with Nvidia GPU runtime support

2 points

8 years ago

256.

Ask HN: Quantify OpenGL draw times with points rendering massive overdraw

2 points

10 years ago

257.

Show HN: Skill capsules" for LLMs, a "poor man's continual learning" (github.com/killerstorm)

1 point

6 months ago

258.

Ask HN: In October 2024, is it a good idea to get an RX 7900 XT for ML?

1 point

2 years ago

259.

Show HN: Willitrun – check if any ML model runs on any device (benchmark-backed) (github.com/smoothyy3)

1 point

2 months ago

260.

Principally new search

1 point

7 years ago

261.

Show HN: Turkish Sieve Engine – Reaching 1.1T-Items/S on a Single GPU (github.com/bilgisofttr)

1 point

4 months ago

262.

C# Hotspot Parallelization by Cekirdekler API (GPGPU)(multi Device)(OpenCL)

1 point

9 years ago

263.

Show HN: PrivaKit – A zero-upload AI workspace in the browser via WebGPU

1 point

2 months ago

264.

Show HN: A Open Source Claude Code setup to publish Research papers 10x faster (github.com/sunnnybala)

1 point

2 months ago

265.

Tinygrad Nvidia P2P hack on Talos OS: 3 days with AI, would been 2 weeks without

1 point

2 months ago

266.

Show HN: BigBangrs – A (simple, but fun) gravity simulator (github.com/felipellrocha)

1 point

3 months ago

267.

Show HN: Fast-Axolotl – Rust extensions that make Axolotl fine-tuning 77x faster (github.com/neul-labs)

1 point

3 months ago

268.

Show HN: Go LLM inference with a Vulkan GPU back end that beats Ollama's CUDA (github.com/computerex)

1 point

3 months ago

269.

Show HN: Market Trade Simulator for AI Agent with No Strategy Restrictions (github.com/nima555)

1 point

3 months ago

270.

Show HN: NHE – Eliminating Frame Drops in 4K 144Hz via Direct-to-Silicon Logic

1 point

3 months ago