Skip to content

[AutoDeploy] Perf1: 80% Performance for Target Models #5048

@lucaslie

Description

@lucaslie

For a subset of “high priority” models, target hitting 80% of TRTLLM-Pytorch performance

Sub-issues

Metadata

Metadata

Labels

AutoDeploy<NV> AutoDeploy Backend

Type

Projects

Status

Ready

Relationships

None yet

Development

No branches or pull requests

Issue actions