phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 10:54:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Nuke hardware_requirements from SKUs

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-13 16:39:02 -07:00
parent d8b3fdbd54
commit 19a14cd273
4 changed files with 17 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_toolchain/inference/meta_reference/model_parallel.py
View file

@ -79,7 +79,7 @@ class LlamaModelParallelGenerator:
def __enter__(self):
self.group = ModelParallelProcessGroup(
self.model.hardware_requirements.gpu_count,
self.config.model_parallel_size,
init_model_cb=partial(init_model_cb, self.config),
)
self.group.start()