Newborn Newborn Rust RS
↑ 31
volta-forever nbald/volta-forever

Your Tesla V100 is not dead: run unmodified CUDA 13 programs (PyTorch, vLLM, SGLang, llama.cpp) on Volta (sm_70). A compatibility layer in front of NVIDIA's driver library.

HEALTH 80 / Healthy
// solo builder// hidden gem

// momentum

tracking since W47

// why it's here

  • Created 1 day ago and already shipping
  • Built almost entirely by one person
  • Health 80/100 with only 40 stars

// how to help

// readme

volta-forever

Your Tesla V100 is not dead. CUDA 13 dropped Volta. volta-forever brings it back.

Run unmodified CUDA 13 programs on a V100: today’s PyTorch wheels, vLLM, SGLang, llama.cpp. No patch, no rebuild. Put two letters in front of your command:

vf python3 -c "import torch; print(torch.cuda.get_device_name())"    # Tesla V100-SXM2-32GB
vf llama-completion -m model.gguf -p "Hello" -n 48 -ngl 99

For a model demo, see the Ubuntu guides.

What a GPU of 2017 lacks is emulated on what it has: the tensor-core instructions of Turing, Ampere and Blackwell, so your V100 now speaks BF16, FP8 and NVFP4.

Tested on Tesla V100-SXM2-32GB cards with NVIDIA’s driver 580.178.04. What it cannot run it refuses with a reason; LIMITS.md has what does not work, what is slower and what was not tried. Not NVIDIA’s, and not endorsed by NVIDIA.

Read the full README on GitHub β†—

Health score

Is the project alive and maintained right now? A 0–100 pulse recomputed nightly from commit recency, rhythm, how fast issues close, and how quickly PRs get merged.

How it's calculated

Undervalued score

Activity relative to attention (stars + watchers). Above 50 means a lot of activity for a project its size. Recomputed nightly from commit velocity, contributor effort, issue resolution, fork utility, release cadence, and project maturity β€” divided by a logarithmic reach factor.

How it's calculated

Tags

Tags are independent behavioral signals computed nightly. A project can hold multiple at once. They drive the home page sections.

How it's calculated