EngineX-Kunlunxin/r200_8f_xtrt_llm
8
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add pkgs

Browse Source
This commit is contained in:
Yang Jun
2025-08-06 15:49:14 +08:00
parent e80b916c52
commit bf00e72fb2
111 changed files with 21880 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/gptj/run.sh Normal file
View File

@@ -0,0 +1,8 @@
XMLIR_D_XPU_L3_SIZE=0 \
python3 run.py \
--engine_dir=./downloads/gptj-6b/trt_engines/fp16/1-XPU/ \
--hf_model_location=./downloads/gptj-6b \
--max_output_len=2048 \
--performance_test_scale=1x512x512E1x1024x1024E1x2000x64E1x2048x2048E2x512x512E2x1024x1024E2x2000x64E2x2048x2048E4x512x512E\
4x1024x1024E4x2000x64E4x2048x2048E8x512x512E8x1024x1024E8x2000x64 \
--log_level=info