Search: github.com/n0id | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

361.

(ROCm) AMD-GPU-Boost: Unlock Full Performance on Consumer AMD GPUs

8 points

9 months ago

362.

Show HN: A port of DOOM that runs (almost) entirely on the GPU (github.com/jhuber6)

8 points

2 years ago

363.

Public AWS GPU-Optimized Deep Learning AMI Pre-Built with Lots of Things

8 points

10 years ago

364.

Show HN: Hlb-CIFAR10 0.2.0: New world record (~<12.38s) on single-GPU CIFAR10 (github.com/tysam-code)

7 points

3 years ago

365.

Show HN: Docker Model Runner Integrates vLLM for High-Throughput Inference (github.com/docker)

7 points

7 months ago

366.

Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) (github.com/Artain-AI)

7 points

2 days ago

367.

Show HN: Enable Claude to interactively debug your code (github.com/jasonjmcghee)

7 points

a year ago

368.

Show HN: Federation of robots collaboratively train an object manipulation model (github.com/adap)

7 points

a year ago

369.

Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com/Luce-Org)

6 points

2 months ago

370.

Tell HN: Llamacpp now supports unified system RAM offloading on Linux

6 points

2 months ago

371.

Show HN: Less Slow C++ (github.com/ashvardanian)

6 points

a year ago

372.

Show HN: LLGTRT: TensorRT-LLM+Rust server w/ OpenAI-compat and Structured Output (github.com/guidance-ai)

6 points

2 years ago

373.

Show HN: Costanza – an autonomous AI agent that can't be turned off (ahrussell.com)

5 points

a month ago

374.

Show HN: Audio AI had a wild day – 5 major open-source / real-time TTS drops (github.com/FlashLabs-AI-Corp)

5 points

4 months ago

375.

Show HN: Paseo – Open-source coding agent interface (desktop, mobile, CLI)

5 points

2 months ago

376.

Show HN: I built an open-source AI system for drones (github.com/stephansturges)

5 points

3 years ago

377.

The Oats Protocol – Open Agent Tools for Local Coding Agents

5 points

19 days ago

378.

Show HN: LLMKube – Kubernetes for Local LLMs with GPU Acceleration (github.com/defilantech)

5 points

7 months ago

379.

Show HN: WebGPU FTW with Splat-Transform (github.com/playcanvas)

5 points

8 months ago

380.

Show HN: LLMOne – Deploy LLMs from bare metal to production in hours (github.com/EM-GeekLab)

5 points

a year ago

381.

Show HN: Arch-Function: 3B parameter LLM that beats GPT-4o on function calling (huggingface.co)

5 points

2 years ago

382.

Vectorless: open-source PDF chatbot without RAG

4 points

10 months ago

383.

Show HN: FP32 matmul of large matrices up to 24% faster than cuBLAS on a 4090 (github.com/arekpaterek)

4 points

2 years ago

384.

Show HN: A navigable map and recommender for 17M music entities (toposonico.com)

4 points

a month ago

385.

Show HN: Turkish Sieve Engine – GPU-Accelerated Prime Number Generator (github.com/bilgisofttr)

4 points

5 months ago

386.

Show HN: WattSeal – PC power consumption monitor (github.com/Daminoup88)

4 points

3 months ago

387.

Show HN: Vocalinux // 100% offline voice typing for Linux (vocalinux.com)

4 points

4 months ago

388.

Show HN: ReFrame – Linux remote desktop that supports Login on Wayland/TTY (github.com/AlynxZhou)

4 points

4 months ago

389.

Show HN: modal-cuda – CLI to run CUDA .cu programs on Modal GPUs (github.com/ExpressGradient)

4 points

7 months ago

390.

Run 35B LLMs on Dual Pascal GPUs with QLoRA

4 points

8 months ago