xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-27 19:10:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove Phi 4 Flash configuration workaround (#22723)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-08-14 12:03:49 +01:00 committed by GitHub
parent eb08487b18
commit f4efda821d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
vllm/transformers_utils/config.py
View File

@ -449,23 +449,6 @@ def get_config(
raise e
config = _maybe_remap_hf_config_attrs(config)
# Phi4Flash misuses this config as list[int]. Convert it to int and add
# the layer_types list[str] to make it HF compatible
if (config.model_type == "phi4flash"):
# TODO: Remove after the following PR is merged:
# https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning/discussions/6
if not hasattr(config, "layer_types"):
config.layer_types = [
"sliding_attention" if i < config.num_hidden_layers // 2
and i % 2 == 1 else "full_attention"
for i in range(config.num_hidden_layers)
]
# TODO: Remove after the following PR is merged:
# https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning/discussions/7
if isinstance(config.sliding_window, list):
config.sliding_window = next(
filter(None, config.sliding_window), None)
elif config_format == ConfigFormat.MISTRAL:
# This function loads a params.json config which
# should be used when loading models in mistral format