ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python/llm/test/benchmark/igpu-perf
History
Yuwen Hu c9ac39fc1e
Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 
* Add Llama 3.2 to iGPU Perf (#12200)

* Add Llama 3.2 to iGPU Perf

* Downgrade accelerate after step

* Temporarily disable model for test

* Temporarily change ERRORLEVEL check (#12201)

* Restore llama3.2 perf (#12206)

* Revert "Temporarily change ERRORLEVEL check"

This reverts commit 909dbbc930ab4283737161a55bb32006e6ca1991.

* Revert "Temporarily disable model for test"

This reverts commit 95322dc3c6429aa836f21bda0b5ba8d9b48592f8.

---------

Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
2024-10-15 17:44:46 +08:00
..
32-32_int4_fp16.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
32-32_int4_fp16_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
32-32_int4_fp16_438.yaml Add Yi-6B and StableLM to iGPU perf test (#11546) 2024-07-09 18:51:23 +08:00
32-32_int4_fp16_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
32-32_int4_fp16_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
1024-128.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_438.yaml Add Yi-6B and StableLM to iGPU perf test (#11546) 2024-07-09 18:51:23 +08:00
1024-128_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
1024-128_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
1024-128_int4_fp16.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_int4_fp16_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_int4_fp16_438.yaml Add Yi-6B and StableLM to iGPU perf test (#11546) 2024-07-09 18:51:23 +08:00
1024-128_int4_fp16_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
1024-128_int4_fp16_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
1024-128_int4_fp16_loadlowbit.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_int4_fp16_loadlowbit_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
1024-128_int4_fp16_loadlowbit_438.yaml Add Yi-6B and StableLM to iGPU perf test (#11546) 2024-07-09 18:51:23 +08:00
1024-128_int4_fp16_loadlowbit_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
1024-128_int4_fp16_loadlowbit_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
2048-256_int4_fp16.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
2048-256_int4_fp16_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
2048-256_int4_fp16_438.yaml Add Yi-6B and StableLM to iGPU perf test (#11546) 2024-07-09 18:51:23 +08:00
2048-256_int4_fp16_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
2048-256_int4_fp16_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
3072-384_int4_fp16.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
3072-384_int4_fp16_436.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
3072-384_int4_fp16_438.yaml add 3k and 4k input of nightly perf test on iGPU (#11701) 2024-08-01 14:17:46 +08:00
3072-384_int4_fp16_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
3072-384_int4_fp16_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
4096-512_int4_fp16.yaml Update performance test regarding updated default transformers==4.37.0 (#11869) 2024-08-20 17:59:28 +08:00
4096-512_int4_fp16_438.yaml add 3k and 4k input of nightly perf test on iGPU (#11701) 2024-08-01 14:17:46 +08:00
4096-512_int4_fp16_443.yaml Add llama 3.1 in igpu perf (#12194) 2024-10-14 15:14:34 +08:00
4096-512_int4_fp16_445.yaml Add Llama 3.2 to iGPU performance test (transformers 4.45) (#12209) 2024-10-15 17:44:46 +08:00
check_csv_results.py Add check in iGPU perf workflow for results integrity (#11616) 2024-07-18 14:13:16 +08:00