On Friday, May 9, 2025, Karl Semich <baffo32@gmail.com> wrote:
notes regarding possibly making graphics apis (wgpu?) have interoperable buffers with tensor libraries note: i think i already implemented this some years ago, probably for raw opengl or vulkan. dunno where that is
- i don't immediately see a way in wgpu to get a raw pointer - i heard opengl has a raw pointer function - i think wgpu uses opengl ES and vulkan 1657 1702 - because gles, vulkan, metal, direct3d, and anything else, have handles to their buffers, it's intuitive that they must be interoperable -- the handles would be passed. any underlying transformation of the handles to support interprocess use would be documented in the interprocess importer for the backend.
https://github.com/gpuweb/gpuweb/issues/4168#issuecomment-2867906416
Given the high utility of writing "shaders" using a compute library, combined with security, portability, and implementation concerns, it could make sense for this to be an optional extension.
To clarify, this feature would let AI-generated assets be synthesized and displayed on a single accelerator, using existing libraries, with neither having to download and re-upload them to the GPU nor port the generation code to a shader language. It also would let people write pseudo-shaders in many other language and libraries.