biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Improve configs - ModelConfig (#17130)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-30 03:38:22 +01:00
committed by GitHub
parent 2c4f59afc3
commit 13698db634
36 changed files with 490 additions and 648 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/model_loader/neuron.py
View File

@@ -180,7 +180,6 @@ def _get_neuron_config_after_override(default_neuron_config,
NeuronConfig, QuantizationConfig,
SparseAttnConfig)
overridden_neuron_config = overridden_neuron_config or {}
sparse_attn = overridden_neuron_config.pop("sparse_attn", {})
if sparse_attn:
overridden_neuron_config["sparse_attn"] = SparseAttnConfig(