Viewing profile — steeve

XLA uses MLIR very much, the interface to it is StableHLO, which is a MLIR dialect.

> Plus, no need to build XLA using Bazel either! You’re welcome. I don't get it, Bazel is incredible.

sidenote: it is possible to use Vulkan to map GPU memory to CPU space and even map it back to CUDA: https://x.com/steeve/status/2055042304344231978?s=20

consider it done

Weird, because we tried it. It doesn’t show anything? We use the amdsmi to get metrics. I’ll investigate.

sadly, sandboxing is something that can't be upstreamed. this way, sandboxing is kept in zml instead of patching mesa. as for nvtop, great program, but we missed a few features (su…

hi, i'm the founder of https://github.com/zml/zml , very happy with Zig

Misleading title. It's about using their AI service, not the editor.

we (ZML) have been back to following Zig master since std.Io was introduced. It's not that bad tbh. Also most changes really feel like actual improvements to the language on a day …

ZML

tldr: they replaced using protobuf as the type system across language boundaries for FFI with true FFI

i can't help but think of the scammy communication around this on X. and the actual need to be deceitful about it. oh how low the mighty have fallen

very very cool !

This looks incredible, congratulations!

the upside is absolutely worth it

because he was been sending me updates about it for the last two weeks because we've been discussing architecture, optimisations and benchmarks because it's not a 13h old project

he’s been working on it for 2 weeks, as he said somewhere else

sure, i hereby disclose that he left in September i already said in another reply that i knew him personally

the way he came barging through the door doesn’t invite sympathy

well, bazel is by far the most reliable one so I'm not sure why you're complaining