thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)

Browse source
This commit is contained in:
Johannes Gäßler 2025-08-20 16:58:49 +02:00 • committed by GitHub
parent fec9519802
commit 7a6e91ad26
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 32 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/multimodal/MobileVLM.md
View file

@ -194,7 +194,7 @@ llama_print_timings: total time = 44411.01 ms / 377 tokens
## Orin compile and run
### compile
```sh
make GGML_CUDA=1 CUDA_DOCKER_ARCH=sm_87 GGML_CUDA_F16=1 -j 32
make GGML_CUDA=1 CUDA_DOCKER_ARCH=sm_87 -j 32
```
### run on Orin
### case 1