[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. #6438
Artifacts
Produced during runtime
Name | Size | Digest | |
---|---|---|---|
vllm-ascend-ubuntu-24.04-arm-py3.11-wheel
|
490 KB |
sha256:bf197eb4d43ad07d729cc100c7173e83f3c4b370d918eb983345be0b2fff3f0d
|
|
vllm-ascend-ubuntu-24.04-py3.11-wheel
|
499 KB |
sha256:209873f60ce86f1dd6ea59d7159e4bc4359bb8feee6121f8697872c0c2eef681
|
|