kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

chore: PR to fix the formatting errors (#4200)

Browse Source 
* updating the run_dtm_pld.py to handle logits correctly

* following correct code formatting

* Update run_dtm_pld.py to account for correct code formatting

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>

* correct formatting for the multimodal README PR

---------

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: Ubuntu <Azureuser@mayani-nch100-vm1.42fmcfe2wyrepoque0x2bs4uue.jx.internal.cloudapp.net>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
This commit is contained in:
mayani-nv 2025-05-09 16:31:36 -07:00 committed by GitHub
parent aa7300e040
commit fe3a993234
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/models/core/multimodal/README.md
View File

@ -975,11 +975,11 @@ Navigate to the folder `TensorRT-LLM/examples/models/core/multimodal`
1. Download Huggingface weights
```bash
export MODEL_NAME="Phi-4-multimodal-instruct"
export MODEL_NAME="Phi-4-multimodal-instruct"
export HF_DIR="tmp/hf_models/${MODEL_NAME}"
export CKPT_DIR="tmp/trt_models/${MODEL_NAME}/fp16/1-gpu"
export ENGINE_DIR="tmp/trt_engines/${MODEL_NAME}/fp16/1-gpu"
git clone https://huggingface.co/microsoft/${MODEL_NAME} ${HF_DIR}
git clone https://huggingface.co/microsoft/${MODEL_NAME} ${HF_DIR}
```
@ -1005,7 +1005,7 @@ Navigate to the folder `TensorRT-LLM/examples/models/core/multimodal`
*Note: the encoders are not the TRT engines but are pure Pytorch ones*
```bash
python build_multimodal_engine.py --model_type phi-4-multimodal --model_path ${HF_DIR} --output_dir ${ENGINE_DIR}
python build_multimodal_engine.py --model_type phi-4-multimodal --model_path ${HF_DIR} --output_dir ${ENGINE_DIR}
python run.py \
--hf_model_dir ${HF_DIR} \