Merge pull request #78 from Catking14/mlperf-inference-results-scc24

MLPerf inference results scc24 NTHU

Author: arjunsuresh

open/NTHU/code/stable-diffusion-xl/README.md

@@ -0,0 +1 @@
+TBD

open/NTHU/measurements/Kuai-Kuai_702-reference-gpu-pytorch-v2.5.1-scc24-base_cu124/README.md

@@ -0,0 +1,3 @@
+| Model               | Scenario   | Accuracy              |   Throughput | Latency (in ms)   |
+|---------------------|------------|-----------------------|--------------|-------------------|
+| stable-diffusion-xl | offline    | (16.40356, 235.76925) |        0.529 | -                 |

open/NTHU/measurements/Kuai-Kuai_702-reference-gpu-pytorch-v2.5.1-scc24-base_cu124/stable-diffusion-xl/offline/Kuai-Kuai_702-reference-gpu-pytorch-v2.5.1-scc24-base_cu124.json

@@ -0,0 +1,7 @@
+{
+  "starting_weights_filename": "https://github.com/mlcommons/inference/tree/master/text_to_image#download-model",
+  "retraining": "no",
+  "input_data_types": "fp32",
+  "weight_data_types": "fp32",
+  "weight_transformations": "no"
+}

open/NTHU/measurements/Kuai-Kuai_702-reference-gpu-pytorch-v2.5.1-scc24-base_cu124/stable-diffusion-xl/offline/README.md

@@ -0,0 +1,57 @@
+This experiment is generated using the [MLCommons Collective Mind automation framework (CM)](https://github.com/mlcommons/cm4mlops).
+
+*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*
+
+## Host platform
+
+* OS version: Linux-6.8.0-47-generic-x86_64-with-glibc2.35
+* CPU version: x86_64
+* Python version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]
+* MLCommons CM version: 3.1.0
+
+## CM Run Command
+
+See [CM installation guide](https://docs.mlcommons.org/inference/install/).
+
+```bash
+pip install -U cmind
+
+cm rm cache -f
+
+cm pull repo mlcommons@cm4mlops --checkout=9bdfff592f2d9607660fb20125ec620ebedc3758
+
+cm run script \
+	--tags=run-mlperf,inference,_r4.1-dev,_short,_scc24-base \
+	--model=sdxl \
+	--implementation=reference \
+	--framework=pytorch \
+	--category=datacenter \
+	--scenario=Offline \
+	--execution_mode=test \
+	--device=cuda \
+	--quiet \
+	--precision=float16 \
+	--clean
+```
+*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf (CM scripts),
+ you should simply reload mlcommons@cm4mlops without checkout and clean CM cache as follows:*
+
+```bash
+cm rm repo mlcommons@cm4mlops
+cm pull repo mlcommons@cm4mlops
+cm rm cache -f
+
+```
+
+## Results
+
+Platform: Kuai-Kuai_702-reference-gpu-pytorch-v2.5.1-scc24-base_cu124
+
+Model Precision: fp32
+
+### Accuracy Results 
+`CLIP_SCORE`: `16.40356`, Required accuracy for closed division `>= 31.68632` and `<= 31.81332`
+`FID_SCORE`: `235.76925`, Required accuracy for closed division `>= 23.01086` and `<= 23.95008`
+
+### Performance Results 
+`Samples per second`: `0.528528`