alihan/exo
1
0
Fork 0
mirror of https://github.com/exo-explore/exo.git synced 2025-10-23 02:57:14 +03:00
Code Issues Packages Projects Releases Wiki Activity

code-breaking typo

Browse Source 
oops
This commit is contained in:
divinity76
2025-02-06 19:02:02 +01:00
committed by GitHub
parent 05ff20fa89
commit 5fe241ec61
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
exo/inference/tinygrad/models/llama.py
View File

@@ -322,6 +322,6 @@ def fix_bf16(weights: Dict[Any, Tensor]):
}
if getenv("SUPPORT_BF16", 1):
# TODO: without casting to float16, 70B llama OOM on tinybox.
return {k: v.cast(dtypes.float32).cast(dtypes.float16) if v.dtype == dtypes.bfloat16 else v for k, v in weights.items()
return {k: v.cast(dtypes.float32).cast(dtypes.float16) if v.dtype == dtypes.bfloat16 else v for k, v in weights.items()}
# TODO: check if device supports bf16
return {k: v.llvm_bf16_cast(dtypes.half).to(v.device) if v.dtype == dtypes.bfloat16 else v for k, v in weights.items()}