Search: github.com/vrza | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

91.

Show HN: Chonkie Cloud – No-nonsense chunking now on the the cloud

cloud.chonkie.ai

a year ago

6 points

92.

Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090

github.com/Luce-Org

2 months ago

6 points

93.

Show HN: Blink-Edit – Cursor-style next-edit predictions for Neovim (local LLMs)

github.com/BlinkResearchLabs

5 months ago

6 points

94.

Show HN: I'm tired of my LLM bullshitting. So I fixed it

5 months ago

5 points

95.

Show HN: AI Council – multi-model deliberation that runs in the browser

github.com/prijak

4 months ago

5 points

96.

Show HN: I built an AI movie making and design engine in Rust

github.com/storytold

5 months ago

5 points

97.

Show HN: ClawMem – Open-source agent memory with SOTA local GPU retrieval

github.com/yoloshii

3 months ago

5 points

98.

TinyTTS: Ultra-light English TTS (9M params, 20MB), 8x CPU, 67x GPU

4 months ago

5 points

99.

Show HN: Clawbernetes – Replace kubectl with conversation (Rust)

github.com/clawbernetes

4 months ago

5 points

100.

Show HN: Open-source fine-tuning in a Colab notebook

colab.research.google.com

2 years ago

5 points

101.

Show HN: Self-hosted RAG with MCP support for OpenClaw

github.com/2dogsandanerd

5 months ago

4 points

102.

Show HN: NSED is public – Mixture-of-Models to Hit SOTA using self-hosted AI

github.com/peeramid-labs

4 months ago

4 points

103.

Show HN: ArtCraft AI crafting engine, written in Rust

github.com/storytold

5 months ago

4 points

104.

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

github.com/Hobanghann

5 months ago

4 points

105.

Run 35B LLMs on Dual Pascal GPUs with QLoRA

9 months ago

4 points

106.

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

github.com/OrderOneAI

a year ago

3 points

107.

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

a year ago

3 points

108.

Show HN: OctoFlow – A GPU-native programming language

4 months ago

3 points

109.

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

4 months ago

hundredtrillion

3 points

110.

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

3 months ago

3 points

111.

Security Layer 4.0 – First semantic firewall blocks malicious intent"

7 months ago

3 points

112.

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

2 months ago

2 points

113.

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

8 months ago

2 points

114.

Show HN: ArtCraft AI crafting engine, written in Rust

github.com/storytold

5 months ago

2 points

115.

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

github.com/danterolle

7 hours ago

2 points

116.

Show HN: Glq LLM quantization using E8 lattice

github.com/cnygaard

21 days ago

2 points

117.

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

github.com/yousef-rafat

3 months ago

2 points

118.

Show HN: From Claude Code to OpenCode – My Evolution in Vibe AI Engineering

3 months ago

2 points

119.

Show HN: Kiln – WebGPU-native out-of-core volume rendering for multi-GB datasets

github.com/MPanknin

4 months ago

2 points

120.

Show HN: Dia-Jax – A Jax port of the Dia text-to-speech dialogue model

github.com/jaco-bro

a year ago

2 points