|
Download examples/README.md from flashrt/fp4-gemm: direct link, hf CLI and curl.
- Browser
- Download file 302 Bytes
-
https://huggingface.co/flashrt/fp4-gemm/resolve/main/examples/README.md
- Command line
-
hf download hf://flashrt/fp4-gemm/examples/README.md
-
curl -L -o README.md https://huggingface.co/flashrt/fp4-gemm/resolve/main/examples/README.md
302 Bytes
| # fp4-gemm Examples | |
| These examples show direct Hub-style usage of `flashrt/fp4-gemm`. | |
| ```bash | |
| python fp4-gemm/examples/fp4_gemm_linear.py | |
| ``` | |
| The quantization helper is included for validation and small examples. In a | |
| runtime, weights should normally be prepacked and loaded as FP4/SFA/SFB buffers. | |