Search: github.com/pytorch | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

721.

Show HN: Simple VSCode extension to autocomplete Python with a transformer model

5 years ago

3 points

722.

Show HN: Autocomplete Python Code with Transformers

5 years ago

3 points

723.

Show HN: A Geometric Algebra NN Framework (100% on 13-hop reasoning)

github.com/Concode0

3 months ago

3 points

724.

Show HN: ModernBERT in Pure C

github.com/hardik-vala

8 months ago

3 points

725.

Show HN: TrainCheck – Catch ML Training Bugs Before It's Too Late

github.com/OrderLab

10 months ago

3 points

726.

Show HN: Powering React with Python (WASM)

a year ago

3 points

727.

Show HN: Coelanox – auditable inference runtime in Rust (BERT runs today)

2 months ago

3 points

728.

Show HN: Charl – ML language with native tensors and autograd

7 months ago

3 points

729.

Show HN: UHOP – Escaping Nvidia Lock-In with an Open Hardware Optimization Layer

8 months ago

3 points

730.

Show HN: Chisel – Profile GPU Kernels Without a GPU (Nvidia and AMD)

github.com/Herdora

a year ago

technoabsurdist

3 points

731.

Show HN: Streamlined SDXL Fine-Tuning for Rapid AI Model Iteration

github.com/omidsakhi

2 years ago

3 points

732.

Show HN: Lego Meets AI: BricksRL to train your own Lego robot

bricksrl.github.io

2 years ago

3 points

733.

Show HN: LLaMA Nuts and Bolts, A holistic way of understanding how LLMs run

github.com/adalkiran

2 years ago

3 points

734.

Show HN: Python Monitoring for AI: LLMs, OpenAI, Inference, GPUs

github.com/graphsignal

3 years ago

3 points

735.

Ask HN: Which cloud provider offers AMD MI250/MI300?

2 years ago

2 points

736.

Ask HN: How do solo founders find academic co-founders for STTR grants?

4 months ago

2 points

737.

Ask HN: Built a tensor + NN framework entirely in Mojo — feedback?

5 months ago

2 points

738.

Show HN: 5MB Rust binary that runs HuggingFace models (no Python)

github.com/Michael-A-Kuykendall

9 months ago

2 points

739.

Show HN: Speed up model inference on CPU with hand crafted layer implementations

github.com/sushrut141

2 years ago

2 points

740.

Show HN: Mixlab, an ML arch lab in Go. JSON config, Metal and CUDA, 1.6s builds

github.com/mrothroc

2 months ago

2 points

741.

Show HN: Lightning-SimulWhisper: Real-Time ASR for Apple Silicon

github.com/altalt-org

8 months ago

2 points

742.

Show HN: Arkflow(stream processing engine) will soon support Python processors

github.com/arkflow-rs

a year ago

2 points

743.

Are there any open source ML libraries that have good (or any) test coverage?

5 years ago

2 points

744.

Show HN: Proxy Block-CAGE, a new sparse block attention

github.com/iqbal1980

a day ago

2 points

745.

Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy

github.com/timothygao8710

2 days ago

2 points

746.

Show HN: Speakrs Full PyAnnotate pipeline in Rust/ONNX 20-37x times faster macOS

github.com/avencera

a month ago

2 points

747.

Show HN: On-device embedding and vector search for Apple Devices, built in Zig

github.com/emmettmcdow

3 months ago

2 points

748.

Show HN: Lar-JEPA – A Testbed for Orchestrating Predictive World Models

github.com/snath-ai

4 months ago

2 points

749.

Show HN: Sleeping LLM – A language model that remembers by sleeping

github.com/vbario

4 months ago

2 points

750.

Ask HN: Why does single-node DDP sometimes get slower with more GPUs?

4 months ago

2 points