Search: github.com/gspu | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

661.

Node.js bindings for Nvidia cuVS > GPU-accelerated vector search (github.com/638Labs)

2 points

2 months ago

662.

Testers wanted: VM-curator v0.2.0 with GPU pass-through support (github.com/mroboff)

2 points

4 months ago

663.

Show HN: Velda – Run jobs with serverless GPUs, without container images (velda.io)

2 points

24 days ago

664.

I built a pure WGSL LLM engine to run Llama on my Snapdragon laptop GPU (github.com/Beledarian)

2 points

2 months ago

665.

Qwen3.5-35B – 16GB GPU – 100T/s with 120K context AND vision enabled (github.com/willbnu)

2 points

3 months ago

666.

Show HN: Tortuise – Gaussian splatting in your terminal, no GPU required (github.com/buildoak)

2 points

3 months ago

667.

Rore: A GPU-Accelerated UI Framework in Rust (No DOM, No Webview) (github.com/davlatov-tech)

2 points

7 months ago

668.

Show HN: Chisel – AMD GPU development that feels local but runs in the cloud (pypi.org)

2 points

technoabsurdist

a year ago

669.

IPEX-LLM Portable Zip for Ollama on Intel GPU (github.com/intel)

2 points

a year ago

670.

Arrow DataFusion includes Ballista, which does SIMD and GPU vectorized ops (github.com/apache)

2 points

5 years ago

671.

UltrafastSecp256k1 – 4.88M ECDSA signs/s on GPU zero dependencies 12 platforms (github.com/shrec)

2 points

4 months ago

672.

LoudCull – Agentless multi-cloud GPU zombie killer (Python/Terraform) (github.com/daretechie)

2 points

4 months ago

673.

Show HN: ZTerm, a GPU-accelerated terminal emulator built with Rust and GPUI (github.com/zerx-lab)

2 points

4 months ago

674.

Predict your distributed LLM training time before you burn GPU hours (github.com/DebarghaG)

2 points

5 months ago

675.

Show HN: QingMing – Exact vector search on consumer GPUs (no index) (github.com/uulong950)

2 points

5 months ago

676.

Show HN: Shared Device Group – GPU sharing at the Kubernetes scheduler level (github.com/sceneryback)

2 points

5 months ago

677.

MetaXuda – 1.1 Tops GPU Runtime for Apple Silicon ML (Rust and Metal) (github.com/Perinban)

2 points

5 months ago

678.

Duckstation now supports the original SCPH-1002 PlayStation GPU (github.com/stenzek)

2 points

5 months ago

679.

Show HN: Picomon, a minimal TUI monitor for AMD GPUs (github.com/omarkamali)

2 points

6 months ago

680.

Show HN: KV Marketplace – share LLM attention caches across GPUs like memcached (github.com/neelsomani)

2 points

7 months ago

681.

Triplet-extract is a GPU-accelerated Python implementation of Stanford OpenIE (github.com/adlumal)

2 points

7 months ago

682.

NumPy-First AI: Persona-Aware Semantic Models Without GPUs (github.com/farukalpay)

2 points

8 months ago

683.

Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs

2 points

a year ago

684.

Show HN: Ish – a grep like CLI tool using SIMD/GPU alignment, built with Mojo

2 points

totalperspectiv

a year ago

685.

FlashMoE: DeepSeek-R1 671B and Qwen3MoE 235B with 1~2 Intel B580 GPU in IPEX-LLM (github.com/intel)

2 points

a year ago

686.

Infernet: A Peer-to-Peer Distributed GPU Inference Protocol (github.com/profullstack)

2 points

cranberryturkey

a year ago

687.

First Golang Project, CLI System Monitor Tool for CPU and GPU (github.com/nikpocuca)

2 points

a year ago

688.

Inframon – Monitor Local Network Devices (e.g., GPU Usage on Apple Silicon) (github.com/metaspartan)

2 points

2 years ago

689.

Btop adds initial Intel GPU support (github.com/aristocratos)

2 points

2 years ago

690.

Show HN: AI Infra for non-Nvidia GPUs (github.com/felafax)

2 points

2 years ago