Search: modal.com | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Doing cheap PyTorch inference with Modal.com

fikisipi.substack.com

3 years ago

6 points

2.

No Local GPU? No Problem Running Andrej Karpathy’s NanoGPT on Modal.com

martincapodici.com

3 years ago

3 points

3.

Fast, lazy container loading in modal.com [video]

2 years ago

1 points

4.

Deploying AI-powered Django apps to Modal.com

2 years ago

1 points

5.

Show HN: AI that generates 3blue1brown-style explainer videos

a year ago

93 points

6.

Show HN: I Built an Open Source API with Insanely Fast Whisper and Fly GPUs

github.com/JigsawStack

2 years ago

13 points

7.

Show HN: isometric.nyc/snow

4 months ago

10 points

8.

Ask HN: Which serverless GPU websites have you tried and which one was best?

3 years ago

9 points

9.

Ask HN: Best cloud GPU solution for inference API?

3 years ago

4 points

10.

Show HN: An unstructured data workspace for data transformations with LLM

3 months ago

4 points

11.

Show HN: Tarot Card Generator

2 years ago

3 points

12.

Show HN: Stable Diffusion Pokémon Cards

modal-labs-example-text-to-pokemon-fastapi-app.modal.run

3 years ago

3 points

13.

Show HN: Tokiwi – An online tokenizer for any Hugging Face model

a year ago

2 points

14.

Ask HN: Looking for empirical advices on "serverless" ML hosting

2 years ago

tonyabracadabra

2 points

15.

Show HN: I hate paying for GPUs while developing – this is how I solved it

adithyask.medium.com

9 months ago

1 points

16.

Ask HN: What Inference Server do you use to host TTS Models?

a year ago

1 points

17.

Instructor with Jason Liu

2 years ago

1 points

18.

DoppelBot: Replace Your CEO with an LLM

a year ago

232 points

19.

The Missing Nvidia GPU Glossary

a year ago

230 points

20.

'I paid for the whole GPU, I am going to use the whole GPU'

a year ago

154 points

21.

Keeping 20k GPUs healthy

5 months ago

134 points

22.

We reverse-engineered Flash Attention 4

9 months ago

134 points

23.

Lambda on hard mode: serverless HTTP in Rust

2 years ago

131 points

24.

Static IPs for Serverless Containers

2 years ago

125 points

25.

We built a cloud GPU notebook that boots in seconds

8 months ago

91 points

26.

Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint

a month ago

91 points

27.

Three types of LLM workloads and how to serve them

5 months ago

75 points

28.

Linear Programming for Fun and Profit

a year ago

62 points

29.

GPU memory snapshots: sub-second startup (2025)

5 months ago

27 points

30.

Boosting multimodal inference performance by >10% with a single Python dict

2 months ago

16 points