vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix docs regarding GGML_HIP

Browse source
This commit is contained in:
Tristan Druyen 2024-11-26 17:00:11 +01:00
parent 81d7fee6c2
commit 8e205ca2c0
No known key found for this signature in database
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/build.md
View file

@ -221,7 +221,7 @@ You can download it from your Linux distro's package manager or from here: [ROCm
- Using `make`: - Using `make`:
```bash ```bash
make GGML_HIPBLAS=1 make GGML_HIP=1
``` ```
- Using `CMake` for Linux (assuming a gfx1030-compatible AMD GPU): - Using `CMake` for Linux (assuming a gfx1030-compatible AMD GPU):
```bash ```bash
@ -249,7 +249,7 @@ You can download it from your Linux distro's package manager or from here: [ROCm
- Using `make` (example for target gfx1030, build with 16 CPU threads): - Using `make` (example for target gfx1030, build with 16 CPU threads):
```bash ```bash
make -j16 GGML_HIPBLAS=1 GGML_HIP_UMA=1 AMDGPU_TARGETS=gfx1030 make -j16 GGML_HIP=1 GGML_HIP_UMA=1 AMDGPU_TARGETS=gfx1030
``` ```
- Using `CMake` for Windows (using x64 Native Tools Command Prompt for VS, and assuming a gfx1100-compatible AMD GPU): - Using `CMake` for Windows (using x64 Native Tools Command Prompt for VS, and assuming a gfx1100-compatible AMD GPU):