[Bugfix]:replace npu_incre_flash_attention with npu_fused_infer_atten… #7909
Artifacts
Produced during runtime
Name | Size | Digest | |
---|---|---|---|
vllm-ascend-ubuntu-24.04-arm-py3.11-wheel
|
504 KB |
sha256:46ec8bf8a431004434da0439d1af83037527f22dfac49a3c3f0dcc8d6504b13c
|
|
vllm-ascend-ubuntu-24.04-py3.11-wheel
|
513 KB |
sha256:de9998fd0df69105c7b839acc30d00d1acd8638c9127a6f5dbf47ed4dcf99184
|
|