Skip to content

[Bugfix] Fix ascend config for qwen3-next #3305

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −2
Open

[Bugfix] Fix ascend config for qwen3-next #3305

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions vllm_ascend/patch/platform/patch_common/patch_mamba_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,10 @@ def verify_and_update_config(cls, vllm_config) -> None:
logger = init_logger(__name__)
# Enable FULL_AND_PIECEWISE by default
MambaModelConfig.verify_and_update_config(vllm_config)
ascend_config = get_ascend_config()
try:
ascend_config = get_ascend_config()
except RuntimeError:
ascend_config = None

cache_config = vllm_config.cache_config
model_config = vllm_config.model_config
Expand All @@ -41,7 +44,9 @@ def verify_and_update_config(cls, vllm_config) -> None:
num_kv_heads=model_config.get_num_kv_heads(parallel_config),
head_size=model_config.get_head_size(),
dtype=kv_cache_dtype,
use_mla=model_config.use_mla or ascend_config.use_sfa).page_size_bytes
use_mla=model_config.use_mla,
use_sfa=ascend_config.use_sfa
if ascend_config is not None else False).page_size_bytes

model_cls, _ = ModelRegistry.resolve_model_cls(
model_config.architecture,
Expand Down
Loading