vllm/model_executor/layers/linear.py · e392d858311a345104ce727e7301476664b3ae53 · OpenDAS / vllm_cscc · GitLab

"vscode:/vscode.git/clone" did not exist on "781096e385112f799c2b12a9aa2660b85efaf983"

Find file Blame History Permalink

[Core] Refactor `QKVCrossParallelLinear` implementation to support BNB 4-bit quantization (#14545) · e392d858
Isotr0py authored Mar 12, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
e392d858

linear.py 61.6 KB