Blame for README.md

---
license: mit
tags:
  - llama-cpp
  - gguf
  - ripple
  - ricursive
  - cuda
  - blackwell
  - ml-intern
---

[![Built with ML Intern](https://huggingface.co/datasets/huggingface/badges/resolve/main/built-with-ml-intern-sm.svg)](https://hf.co/chat?mode=ml-intern)

# llama.cpp + ricursive (Ripple-65B) — prebuilt CUDA binaries

Prebuilt binaries of llama.cpp with support for the `ricursive` architecture
([ricursiveAI/Ripple-65B-Preview](https://huggingface.co/ricursiveAI/Ripple-65B-Preview)),
which is not in upstream llama.cpp yet ([PR #31692](https://github.com/ggml-org/llama.cpp/pull/31692)).

Built from llama.cpp @ [`9e2a04a`](https://github.com/ggml-org/llama.cpp/commit/9e2a04a439edc49f08c5acdafefae19dfa25a658)
+ [AtomicChat's `ricursive-port.patch`](https://huggingface.co/AtomicChat/Ripple-65B-Preview-GGUF),
with CUDA 12.8 for **sm_120 (RTX PRO 6000 Blackwell)** only, CPU backend with runtime-dispatched variants.
The exact build script is [`build.sh`](build.sh) in this repo (reproducible with `bash build.sh`
in an `nvidia/cuda:12.8.1-devel-ubuntu22.04` container).

## Files

| File | What | Use |
|---|---|---|
| `llama-ricursive-cuda128-sm120.tar.gz` | `llama-server` + `libggml*` shared libs (`bin/`) | Untar, run `bin/llama-server -m <gguf> --jinja -c 65536 -ngl all`. This is what [akhaliq/ripple-65b-zerogpu](https://huggingface.co/spaces/akhaliq/ripple-65b-zerogpu) downloads at startup |
| `llama_cpp_python-0.3.36+cu128.ricursive-py3-none-linux_x86_64.whl` | `llama-cpp-python` 0.3.36 with the same patched llama.cpp | `pip install https://huggingface.co/akhaliq/llama-cpp-ricursive-cuda120/resolve/main/llama_cpp_python-0.3.36%2Bcu128.ricursive-py3-none-linux_x86_64.whl` |

## Notes

- Linux x86_64, glibc (built on Ubuntu 22.04). GPU: Blackwell sm_120 only — other cards need a rebuild with different `CMAKE_CUDA_ARCHITECTURES`.
- GGUFs that work with this: [AtomicChat/Ripple-65B-Preview-GGUF](https://huggingface.co/AtomicChat/Ripple-65B-Preview-GGUF) (BF16 / Q8_0 / Q4_K_M) and [prometheusAIR/Ripple-65B-Preview-GGUF](https://huggingface.co/prometheusAIR/Ripple-65B-Preview-GGUF) (Q8_0 / Q6_K_XL / Q6_K) — note prometheusAIR ship their own patch; binaries here follow AtomicChat's port, both load the same files per AtomicChat's card.
- Once PR #31692 merges upstream, prefer official llama.cpp releases; this repo is a stopgap.

MIT (llama.cpp, llama-cpp-python) · GGUF weights are Apache-2.0 via Ricursive.