mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-27 22:23:25 +08:00
4bb65f216f
* Update TensorRT-LLM --------- Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com> Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
17 lines
360 B
Bash
Executable File
17 lines
360 B
Bash
Executable File
#!/bin/bash
|
|
set -ex
|
|
|
|
PROMPT="Tell a story"
|
|
LLAMA_MODEL_DIR=$1
|
|
|
|
|
|
python3 llm_examples.py --task run_llm_with_quantization \
|
|
--prompt="$PROMPT" \
|
|
--hf_model_dir=$LLAMA_MODEL_DIR \
|
|
--quant_type="int4_awq"
|
|
|
|
python3 llm_examples.py --task run_llm_with_quantization \
|
|
--prompt="$PROMPT" \
|
|
--hf_model_dir=$LLAMA_MODEL_DIR \
|
|
--quant_type="fp8"
|