mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-31 08:11:27 +08:00
This commit: * extends existing factory interfaces to enable Mistral3 in AutoDeploy. * adds a Mistral3 VLM factory. * adds various model patches for pixtral (the vision model) and mistral3 to make the VLM export compliant. * adjusts checkpoint loading code to take possible parameter name conversions into account. * fixes a sampling bug (the `end_id` needs to be take into account when sampling, but it is not included in the stop words' token IDs). Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| _utils_test | ||
| unit | ||