[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. #6432
Artifacts
Produced during runtime
Name | Size | Digest | |
---|---|---|---|
vllm-ascend-ubuntu-24.04-arm-py3.11-wheel
|
490 KB |
sha256:62026adb75b3a8c04c650398e7ea6985b7a4a41d4ee864364b69e3221964a343
|
|
vllm-ascend-ubuntu-24.04-py3.11-wheel
|
499 KB |
sha256:c8f9f103761322450312bf6ebcc59e7c3619992b012c4b85916436f11c9d7de0
|
|