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 14, 05:30 UTC
Add Phi4FlashForCausalLM to _PREVIOUSLY_SUPPORTED_MODELS (#25832)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Thomas Parnell committed
Sep 29, 2025 at 07:08 UTC
219cfbe7f6992120465c01c9c85a138be93204b2
1 file changed
+1
vllm/model_executor/models/registry.py
+1
@@ -333,6 +333,7 @@ _SUBPROCESS_COMMAND = [
333
334
_PREVIOUSLY_SUPPORTED_MODELS = {
335
"Phi3SmallForCausalLM": "0.9.2",
336
+ "Phi4FlashForCausalLM": "0.10.2",
337
# encoder-decoder models except whisper
338
# have been removed for V0 deprecation.
339
"BartModel": "0.10.2",