tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-06 09:10:11 -04:00
Code Issues Packages Projects Releases Wiki Activity

Docs: add instructions for adding backends (#14889)

Browse Source
This commit is contained in:
Aman Gupta
2025-07-27 09:36:43 +08:00
committed by GitHub
parent 66906cd82a
commit 446595b9b3
5 changed files with 14744 additions and 13074 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
scripts/create_ops_docs.py
View File

@@ -112,6 +112,11 @@ class DocsGenerator:
lines.append("")
lines.append("List of GGML operations and backend support status.")
lines.append("")
lines.append("## How to add a backend to this table:")
lines.append("")
lines.append("1. Run `test-backend-ops support --output csv` with your backend name and redirect output to a csv file in `docs/ops/` (e.g., `docs/ops/CUDA.csv`)")
lines.append("2. Regenerate `/docs/ops.md` via `./scripts/create_ops_docs.py`")
lines.append("")
lines.append("Legend:")
lines.append("- ✅ Fully supported by this backend")
lines.append("- 🟡 Partially supported by this backend")