Search: github.com/gpujs | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

Implementing ray serve multi GPUs with autoscaling for stable-diffusion-webui (github.com/AUTOMATIC1111)

1 point

3 years ago

152.

Nvflashk – Flash any BIOS to Nvidia GPUs – Safe board ID bypass up to 4xx series (github.com/notfromstatefarm)

1 point

3 years ago

153.

Fast and Memory efficient lattice Boltzmann CFD software, running on all GPUs (github.com/ProjectPhysX)

1 point

3 years ago

154.

MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs (github.com/kuleshov)

1 point

3 years ago

155.

TRTorch: PyTorch/TorchScript Compiler for Nvidia GPUs Using TensorRT (github.com/NVIDIA)

1 point

5 years ago

156.

CUDA on Intel GPUs in Rust (github.com/vosen)

1 point

6 years ago

157.

Purge-nvda: Optimize external graphics for Macs with discrete Nvidia GPUs (github.com/mayankk2308)

1 point

6 years ago

158.

Build and Run Docker Containers Leveraging Nvidia GPUs (github.com/NVIDIA)

1 point

thushanfernando

7 years ago

159.

Gpu_monitor: Monitor your GPUs whether they are on a computer or in a cluster (github.com/msalvaris)

1 point

8 years ago

160.

Set-eGPU: allow use of external GPUs in macOS, even on internal displays (github.com/mayankk2308)

1 point

8 years ago

161.

Monitor your GPUs whether they are on a single computer or in a cluster (github.com/msalvaris)

1 point

8 years ago

162.

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

1 point

11 years ago

163.

Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model (github.com/KittenML)

1003 points

10 months ago

164.

Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU (github.com/xaskasdf)

395 points

4 months ago

165.

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (github.com/unslothai)

385 points

3 years ago

166.

Show HN: Generative Fill with AI and 3D (github.com/fill3d)

360 points

3 years ago

167.

Launch HN: Silurian (YC S24) – Simulate the Earth

338 points

2 years ago

168.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com/alainnothere)

265 points

3 months ago

169.

Launch HN: Hatchet (YC W24) – Open-source task queue, now with a cloud version

245 points

2 years ago

170.

Less Slow C++ (github.com/ashvardanian)

198 points

a year ago

171.

Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers

189 points

2 years ago

172.

Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com/felafax)

189 points

2 years ago

173.

Ollama for Linux – Run LLMs on Linux with GPU Acceleration (github.com/jmorganca)

173 points

3 years ago

174.

Show HN: TensorDock Core GPU Cloud – GPU servers from $0.29/hr (tensordock.com)

147 points

4 years ago

175.

Launch HN: ParaQuery (YC X25) – GPU Accelerated Spark/SQL

135 points

a year ago

176.

Show HN: ART – a new open-source RL framework for training agents (github.com/OpenPipe)

116 points

a year ago

177.

Show HN: Open-source real time data framework for LLM applications (getindexify.ai)

92 points

2 years ago

178.

Tell HN: GpuOwl/PRPLL, GPU software used to find the largest prime number

72 points

2 years ago

179.

Show HN: A personalised AI tutor with < 1s voice responses (educationbot.cerebrium.ai)

72 points

2 years ago

180.

Show HN: A GPU-accelerated binary vector index (rlafuente.com)

65 points

a year ago