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

[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2025-12-05 12:48:43 -05:00
committed by GitHub
parent dff0a2b394
commit 66e674cdd5
22 changed files with 367 additions and 325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/model_executor/models/vision.py
View File

@@ -11,7 +11,7 @@ import torch
from transformers import PretrainedConfig
from vllm.attention.backends.registry import AttentionBackendEnum
from vllm.config import VllmConfig
from vllm.config import VllmConfig, get_current_vllm_config
from vllm.distributed import (
get_tensor_model_parallel_rank,
get_tensor_model_parallel_world_size,
@@ -91,10 +91,7 @@ def get_vit_attn_backend(
if attn_backend_override is not None:
return attn_backend_override
# Lazy import to avoid circular dependency
from vllm.attention.selector import get_env_variable_attn_backend
selected_backend: AttentionBackendEnum | None = get_env_variable_attn_backend()
selected_backend = get_current_vllm_config().attention_config.backend
if selected_backend is not None:
return selected_backend