vllm/v1/worker/gpu_model_runner.py · 82c795d6f28ee365bfa822f30612e5da35c93fc0 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Perf] Optimize EAGLE prepare_inputs_padded with triton kernels (#28597) · 1986de13
Benjamin Chislett authored Nov 28, 2025
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
```
1986de13

gpu_model_runner.py 229 KB