mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-19 17:25:17 +08:00
Signed-off-by: Chang Liu (Enterprise Products) <liuc@nvidia.com> Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com> Signed-off-by: Zhenhua Wang <zhenhuaw@nvidia.com> Co-authored-by: Freddy Qi <junq@nvidia.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Zhenhua Wang <zhenhuaw@nvidia.com>
9 lines
135 B
YAML
9 lines
135 B
YAML
linear:
|
|
type: default
|
|
teacache:
|
|
enable_teacache: true
|
|
teacache_thresh: 0.2
|
|
parallel:
|
|
dit_cfg_size: 1
|
|
dit_ulysses_size: 1
|