[HN Gopher] Getting DeepSeek-OCR working on an Nvidia Spark via ...
___________________________________________________________________
Getting DeepSeek-OCR working on an Nvidia Spark via brute force
with Claude Code
Author : simonw
Score : 96 points
Date : 2025-10-20 17:24 UTC (1 days ago)
(HTM) web link (simonwillison.net)
(TXT) w3m dump (simonwillison.net)
| syntaxing wrote:
| Ehh, is it cool and time savings that it figured it out? Yes. But
| the solution was to get a "better" version prebuilt wheel package
| of PyTorch. This is a relatively "easy" problem to solve
| (figuring out this was the problem does take time). But it's
| (probably, I can't afford one) going to be painful when you want
| to upgrade the cuda version or specify a specific version. Unlike
| a typical PC, you're going to need to build a new image and flash
| it. I would be more impressed when a LLM can do this end to end
| for you.
| sh3rl0ck wrote:
| Pytorch + CUDA is a headache I've seen a lot of people have at
| my uni, and one I've never had to deal with thanks to uv. Good
| tooling really does go a long way in these things.
|
| Although, I must say that for certain docker pass through
| cases, the debugging logs just aren't as detailed
| ComputerGuru wrote:
| uv doesn't fundamentally solve the issues. It didn't invent
| venv or pip.
|
| What fundamentally solves the issue is to use an onnx version
| of the model.
| simonw wrote:
| Do you know if it's possible to run ONNX versions of models
| on a Mac?
|
| I should try those on the NVIDIA Spark, be interesting to
| see if they are easy to work with on ARM64.
| BoredPositron wrote:
| Compute well spent... finding out to download a version and
| hardware appropriate wheel.
| Zopieux wrote:
| Gotta keep the hype up!
| varispeed wrote:
| I am the only one seeing this Nvidia Spark as meh?
|
| I had it in my cart, but then watched few videos from influencers
| and it looks like power of this thing doesn't match the hype.
___________________________________________________________________
(page generated 2025-10-21 23:00 UTC)