A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 02:00 UTC
[Bugfix] Fix `HfExampleModels.find_hf_info` (#12223)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jan 20, 2025 at 23:35 UTC
18572e3384a6f55a7589dd81e1f3f70f7dd73e3a
1 file changed
+5
tests/models/registry.py
+5
@@ -302,6 +302,11 @@ class HfExampleModels:
302
if info.default == model_id:
303
return info
304
305
+ # Fallback to extras
306
+ for info in self.hf_models.values():
307
+ if any(extra == model_id for extra in info.extras.values()):
308
+ return info
309
+
310
raise ValueError(f"No example model defined for {model_id}")
311
312