Search: github.com/gpujs | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

91.

Rvidia-exporter – Prometheus metrics exporter for Nvidia GPUs (github.com/neo-airouter)

3 points

a month ago

92.

AMD ROCm: 40x slower at linear algebra than older Nvidia GPUs (github.com/ROCm)

3 points

2 months ago

93.

Show HN: AudioGhost AI – Run Meta's Sam-Audio on Consumer GPUs (4GB-6GB VRAM) (github.com/0x0funky)

3 points

5 months ago

94.

Shimmy v1.7.0: Running 42B Moe Models on Consumer GPUs with 99.9% VRAM Reduction (github.com/Michael-A-Kuykendall)

3 points

8 months ago

95.

LLM inference load balancer optimized for AMD Radeon VII GPUs (github.com/janit)

3 points

2 months ago

96.

Show HN: Local video search with Qwen3-VL: no API, runs on Apple Silicon, GPUs (github.com/ssrajadh)

3 points

2 months ago

97.

Java Running Directly on Apple Silicon GPUs with TornadoVM Metal Codegen (github.com/beehive-lab)

3 points

3 months ago

98.

Show HN: UHOP – An Open Hardware Optimization Platform for GPUs (github.com/sevenloops)

3 points

7 months ago

99.

ZLUDA - CUDA on Non-Nvidia GPUs (github.com/vosen)

3 points

10 months ago

100.

AdaptiveCpp: Implementation of SYCL and C++ CPUs and GPUs (github.com/AdaptiveCpp)

3 points

a year ago

101.

Show HN: Python Monitoring for AI: LLMs, OpenAI, Inference, GPUs (github.com/graphsignal)

3 points

3 years ago

102.

Show HN: Run and fine-tune 175B+ LMs in Colab using a P2P network of GPUs (github.com/bigscience-workshop)

3 points

3 years ago

103.

Show HN: DreamBooth Models on Serverless GPUs (github.com/mystic-ai)

3 points

3 years ago

104.

KataGo: AlphaZero-like training with only 47 GPUs (github.com/lightvector)

3 points

6 years ago

105.

Build and run Docker containers leveraging Nvidia GPUs (github.com/NVIDIA)

3 points

11 years ago

106.

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

2 points

a month ago

107.

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

2 points

22 days ago

108.

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

2 points

4 months ago

109.

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

2 points

6 months ago

110.

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

2 points

7 months ago

111.

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

2 points

8 months ago

112.

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

2 points

a year ago

113.

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

2 points

2 years ago

114.

Kyanite: NN inference library, in/for Rust, using CPU or Nvidia GPUs (github.com/KarelPeeters)

2 points

3 years ago

115.

Show HN: Profine – Profile and rewrite your ML training loop on real GPUs (github.com/ProfineAI)

2 points

24 days ago

116.

Show HN: Inferential – Multi-robot inference scheduling on shared GPUs (github.com/nalinraut)

2 points

3 months ago

117.

Show HN: Run autoresearch on a gaming PC (Windows and RTX GPUs fork) (github.com/jsegov)

2 points

3 months ago

118.

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

2 points

4 months ago

119.

Show HN: Free GPUs in your terminal for learning CUDA (github.com/RohanAdwankar)

2 points

7 months ago

120.

GPT-OSS from Scratch on AMD GPUs (github.com/tuanlda78202)

2 points

8 months ago