phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 14:20:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename quant types to use _mixed naming

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-07 12:57:58 -07:00
parent b239c57c54
commit 76004eacb4
3 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/models/llama/llama4/quantization/loader.py
View file

@ -91,7 +91,7 @@ def convert_to_quantized_model(
log_status(f"Rank {rank}: Quantizing int4 weights from bf16")
def apply_quantization(_, weight):
return quantize_int4(weight, output_device=torch.device("cuda"))
return quantize_int4(weight, fp8_activation_scale_ub, output_device=torch.device("cuda"))
else:
fp8_scales_path = os.path.join(checkpoint_dir, f"fp8_scales_{rank}.pt")