Search: github.com/vr6 | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

391.

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model (github.com/cactus-compute)

776 points

25 days ago

392.

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com/antoinezambelli)

687 points

18 days ago

393.

Show HN: InvokeAI, an open source Stable Diffusion toolkit and WebUI (github.com/invoke-ai)

414 points

4 years ago

394.

Show HN: Doom (1993) in a PDF (doompdf.pages.dev)

369 points

a year ago

395.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com/alainnothere)

265 points

3 months ago

396.

Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers

189 points

2 years ago

397.

Show HN: WebGPU enables local LLM in the browser – demo site with AI chat (andreinwald.github.io)

145 points

10 months ago

398.

Show HN: Ephe – A minimalist open-source Markdown paper for today (github.com/unvalley)

143 points

a year ago

399.

Show HN: I made a volumetric audio visualizer (a-sumo.github.io)

90 points

4 years ago

400.

Show HN: AudioNimbus – Steam Audio's immersive spatial audio, now in Rust (github.com/MaxenceMaire)

77 points

a year ago

401.

Show HN: Crazierl – An Erlang Operating System (crazierl.org)

72 points

2 months ago

402.

Show HN: Open Sourcing Our No-Code WebXR Editor After 5 Years of Development (github.com/transferthought)

67 points

2 years ago

403.

Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts (github.com/Zyora-Dev)

58 points

3 months ago

404.

Launch HN: General Instinct (YC P26) – Frontier models on edge devices

51 points

18 hours ago

405.

Show HN: I built a RISC-V emulator that runs DOOM (github.com/lalitshankarch)

50 points

a month ago

406.

Asking for help: Please encourage Microsoft to add AAAA records for artefacts

36 points

4 years ago

407.

Show HN: Local task classifier and dispatcher on RTX 3080 (github.com/resilientworkflowsentinel)

26 points

4 months ago

408.

Show HN: Bashtorio – Factorio-Like in the Browser Backed by a Linux VM (bashtorio.xyz)

23 points

4 months ago

409.

Ask: How to announce my 14 years old web development framework?

22 points

8 years ago

410.

Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines (github.com/kvcache-ai)

20 points

2 years ago

411.

Show HN: Demon – open-source real-time music diffusion engine, 25Hz local GPU (daydreamlive.github.io)

17 points

ryanontheinside

10 days ago

412.

Show HN: EVRTHN.com, a Search Engine for the “Metaverse” (evrthn.com)

17 points

4 years ago

413.

Show HN: Finetune Llama-3.1 2x faster in a Colab (colab.research.google.com)

16 points

2 years ago

414.

Show HN: Salad, a distributed cloud for AI (like Airbnb for GPUs)

15 points

2 years ago

415.

Achieving a zero-downtime Postgres major version upgrade (medplum.com)

15 points

a year ago

416.

Ping.gg monitoring engine now open source (Go)

15 points

11 years ago

417.

Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill (github.com/kvcache-ai)

14 points

a year ago

418.

Show HN: Willow Inference Server: Optimized ASR/TTS/LLM for Willow/WebRTC/REST (github.com/toverainc)

13 points

3 years ago

419.

Show HN: Lightweight Llama3 Inference Engine – CUDA C (github.com/abhisheknair10)

12 points

a year ago

420.

Show HN: Automatic 1111, but as a Python Package (github.com/saketh12)

11 points

2 years ago