Search: github.com/vr6 | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

451.

Show HN: HORenderer3: A C++ software renderer implementing OpenGL 3.3 pipeline

github.com/Hobanghann

5 months ago

4 points

452.

Run 35B LLMs on Dual Pascal GPUs with QLoRA

9 months ago

4 points

453.

Show HN: Klartraum, a neural rendering inference engine

github.com/fortmeier

a year ago

4 points

454.

Show HN: FlowG – A low-code log management software proof of concept

github.com/link-society

2 years ago

4 points

455.

Show HN: Quickwit 0.6 – OSS Elasticsearch alternative on object storage

3 years ago

4 points

456.

Show HN: A reasoning model that infers over whole tasks in 1ms in latent space

github.com/OrderOneAI

a year ago

3 points

457.

Show HN: Turn any ComfyUI workflow into a web app or API

a year ago

3 points

458.

Show HN: OctoFlow – A GPU-native programming language

4 months ago

3 points

459.

Status of Linux MMU on RISC-V Sipeed M1 / Maixduino / K210

3 years ago

3 points

460.

Seeking Advice on Improving OCR for Watermarked PDFs in My RAG Pipeline

4 months ago

hundredtrillion

3 points

461.

Standalone WebGL, or a browser for the Oculus Rift

12 years ago

3 points

462.

Show HN: Ephe – A Minimalist Open-Source Markdown Paper for Today

github.com/unvalley

a year ago

3 points

463.

Show HN: Velda – Run any command directly on cloud compute

9 months ago

3 points

464.

Show HN: Benlink – Control Benshi Radios (e.g. BTech UV-Pro) with Python

github.com/khusmann

a year ago

3 points

465.

Show HN: Valkyr LM Inference with Realtime Guarantees

github.com/Foundation42

2 months ago

3 points

466.

Tq-KV – Rust implementation of TurboQuant that works on GGUF models

3 months ago

3 points

467.

Show HN: I built an AI desktop Waifu that remembers you

github.com/buyve

4 months ago

3 points

468.

Show HN: Buildlog – Record AI coding sessions as replayable workflow recipes

5 months ago

3 points

469.

Security Layer 4.0 – First semantic firewall blocks malicious intent"

7 months ago

3 points

470.

Open-TeleVision Control Robots even away 3000 mile

2 years ago

3 points

471.

Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs

2 months ago

2 points

472.

Why stop at 1M tokens when you can have 10M?

8 months ago

2 points

473.

Show HN: Velda – Run jobs with serverless GPUs, without container images

a month ago

2 points

474.

Show HN: ArtCraft AI crafting engine, written in Rust

github.com/storytold

5 months ago

2 points

475.

Show HN: JadeAI – Resume builder with AI parsing, 50 templates, and self-hosting

4 months ago

2 points

476.

Show HN: Mantella – Talk to AI-Powered NPCs in Skyrim

github.com/art-from-the-machine

3 years ago

Art_F_T_Machine

2 points

477.

Show HN: Loqi, a "local-first" translation tool using Ollama/llama.cpp

github.com/danterolle

2 days ago

2 points

478.

Show HN: Glq LLM quantization using E8 lattice

github.com/cnygaard

22 days ago

2 points

479.

Show HN: EDDI – Multi-agent AI engine where agent logic lives in JSON, not code

github.com/labsai

2 months ago

2 points

480.

Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU

github.com/yousef-rafat

3 months ago

2 points