[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. #6650
Artifacts
Produced during runtime
Name | Size | Digest | |
---|---|---|---|
vllm-ascend-ubuntu-24.04-arm-py3.11-wheel
|
488 KB |
sha256:90f48dad07d5bd8004484319fd5a58e339cbc795a7f34f9101b6bab9ff94c3f5
|
|
vllm-ascend-ubuntu-24.04-py3.11-wheel
|
497 KB |
sha256:057c6412eac4f719660e7acf27c81e90f488b18b0d205e2d53cb298f7a9929ee
|
|