Results from self hosted Github actions - NVIDIARTX4090

GATEOverflow · Feb 8, 2025 · 3962eaa · 3962eaa
1 parent 3528411
commit 3962eaa
Show file tree

Hide file tree

Showing 27 changed files with 741 additions and 741 deletions.
diff --git a/open/MLCommons/measurements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/README.md b/open/MLCommons/measurements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/README.md
@@ -1,3 +1,3 @@
 | Model               | Scenario   | Accuracy              |   Throughput | Latency (in ms)   |
 |---------------------|------------|-----------------------|--------------|-------------------|
-| stable-diffusion-xl | offline    | (16.74778, 233.71855) |        1.314 | -                 |
+| stable-diffusion-xl | offline    | (16.72908, 236.88583) |        1.314 | -                 |
diff --git a/.../arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/README.md b/.../arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/README.md
@@ -38,8 +38,8 @@ Platform: arjun_spr-nvidia-gpu-TensorRT-scc24-base
 Model Precision: int8
 
 ### Accuracy Results 
-`CLIP_SCORE`: `16.74778`, Required accuracy for closed division `>= 31.68632` and `<= 31.81332`
-`FID_SCORE`: `233.71855`, Required accuracy for closed division `>= 23.01086` and `<= 23.95008`
+`CLIP_SCORE`: `16.72908`, Required accuracy for closed division `>= 31.68632` and `<= 31.81332`
+`FID_SCORE`: `236.88583`, Required accuracy for closed division `>= 23.01086` and `<= 23.95008`
 
 ### Performance Results 
-`Samples per second`: `1.31417`
+`Samples per second`: `1.31386`
diff --git a/...arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/accuracy_console.out b/...arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/accuracy_console.out
diff --git a/...rements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-deps.mmd b/...rements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-deps.mmd
diff --git a/...jun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-deps.png b/...jun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-deps.png
diff --git a/...rjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-version-info.json b/...rjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/mlc-version-info.json
diff --git a/...rements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/os_info.json b/...rements/arjun_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/os_info.json
@@ -26,5 +26,5 @@
   ],
   "MLC_HOST_PLATFORM_FLAVOR": "x86_64",
   "MLC_HOST_PYTHON_BITS": "64",
-  "MLC_HOST_SYSTEM_NAME": "541c77252aee"
+  "MLC_HOST_SYSTEM_NAME": "32c682b196d0"
 }
diff --git a/...un_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/performance_console.out b/...un_spr-nvidia-gpu-TensorRT-scc24-base/stable-diffusion-xl/offline/performance_console.out