code-breaking typo

5fe241ec61c9d89157abb2e8f11abb23d8ef4156 · 2025-02-06 19:02:02 +0100 · divinity76

oops

Files touched

M exo/inference/tinygrad/models/llama.py

Diff

commit 5fe241ec61c9d89157abb2e8f11abb23d8ef4156
Author: divinity76 <hans@loltek.net>
Date:   Thu Feb 6 19:02:02 2025 +0100

    code-breaking typo
    
    oops
---
 exo/inference/tinygrad/models/llama.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exo/inference/tinygrad/models/llama.py b/exo/inference/tinygrad/models/llama.py
index bc99fbfd..fbe0d69f 100644
--- a/exo/inference/tinygrad/models/llama.py
+++ b/exo/inference/tinygrad/models/llama.py
@@ -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()}

← 05ff20fa workaround f16 cast ambiguity · back to Exo · update README to better reflect support for other devices li 2c982d92 →