Alpha learning-system executables

Self-contained x86-64 ELFs compiled by the Alpha compiler from one .alpha closure per system/target pairing. Each drives an NVIDIA GPU directly through the RM/UVM interface; there is no CUDA, Python or framework in the executable. They train, resume from a checkpoint and predict through the versioned text-artifact request protocol.

manifest.json is the authority for the current sha256 of every file. Only the RTX 3090 pairings have been run on physical hardware.

File	Target	Bytes	sha256
`bob/bob-rtx3070-sm86.elf`	runpod-nvidia-geforce-rtx3070-sm86	421121	`1615fe4ca6d288a85a65fc20e126cedb0463e4aca6b4e4ba567a655041bf5448`
`bob/bob-rtx3090-sm86.elf`	runpod-nvidia-geforce-rtx3090-sm86	421121	`46365fa882178b0b366a679be0a1e9807c27025b14221f02fef7c53dc4e0a5cc`
`bob/bob-rtx4090-sm89.elf`	runpod-nvidia-geforce-rtx4090-sm89	421121	`f124128ed3359a55f71b1752d0b41440cb69655f5ef9c6e4ef67690c409304ef`
`coppelius/coppelius-rtx3070-sm86.elf`	runpod-nvidia-geforce-rtx3070-sm86	1674316	`04e7f99a386764c747451c9398fbac1b393f48bd9c7efb0b2f59fae5c9e43dfd`
`coppelius/coppelius-rtx3090-sm86.elf`	runpod-nvidia-geforce-rtx3090-sm86	1674316	`5c51766cb6a9a1665e55b5ad6b2b0851b080a21798a37e1ea4edc96d0d489a77`
`coppelius/coppelius-rtx4090-sm89.elf`	runpod-nvidia-geforce-rtx4090-sm89	1674316	`9d60b8819e521690ef1e9bb821be83b53deff655b6566d3b0588b807196fc5a6`

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support