Add binary cache

[pfultz2]

Motivation

Technical Details

Changelog Category

Add a CHANGELOG.md entry for any option other than Not Applicable

• • Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

Follow the LLVM AI Tool Use Policy for contributions using AI.

[gh-app-migraphx-bot-pr-write]

Test	Batch	New Rate (9a8098)	Old Rate (3a503c)*	Diff	Status
torchvision-resnet50	64	2,237.70	3,264.92	-31.46%	🔴
torchvision-resnet50_fp16	64	4,186.67	7,548.67	-44.54%	🔴
torchvision-densenet121	32	554.13	2,483.99	-77.69%	🔴
torchvision-densenet121_fp16	32	2,019.41	5,004.24	-59.65%	🔴
torchvision-inceptionv3	32	1,990.99	2,058.51	-3.28%	✅
torchvision-inceptionv3_fp16	32	4,405.00	4,416.99	-0.27%	✅
cadene-inceptionv4	16	219.30	820.61	-73.28%	🔴
cadene-resnext64x4	16	327.40	782.78	-58.17%	🔴
slim-mobilenet	64	4,361.22	8,386.36	-48.00%	🔴
slim-nasnetalarge	64	191.82	228.86	-16.18%	🔴
slim-resnet50v2	64	2,499.58	3,180.91	-21.42%	🔴
bert-mrpc-onnx	8	1,168.88	1,168.84	0.00%	✅
bert-mrpc-tf	1	494.04	498.63	-0.92%	✅
pytorch-examples-wlang-gru	1	534.02	473.35	12.82%	🔆
pytorch-examples-wlang-lstm	1	364.63	384.83	-5.25%	🔴
torchvision-resnet50_1	1	1,035.29	1,046.63	-1.08%	✅
cadene-dpn92_1	1	450.31	437.32	2.97%	✅
cadene-resnext101_1	1	366.13	365.89	0.07%	✅
onnx-taau-downsample	1	843.87	844.09	-0.03%	✅
dlrm-criteoterabyte	1	1.12	32.42	-96.55%	🔴
dlrm-criteoterabyte_fp16	1	51.96	51.80	0.30%	✅
agentmodel	1	11,598.59	9,209.12	25.95%	🔆
unet_fp16	2	58.70	58.80	-0.17%	✅
resnet50v1_fp16	1	1,359.14	1,366.11	-0.51%	✅
resnet50v1_int8	1	1,637.86	1,883.96	-13.06%	🔴
bert_base_cased_fp16	64	1,098.24	1,098.16	0.01%	✅
bert_large_uncased_fp16	32	345.65	345.59	0.02%	✅
bert_large_fp16	1	206.99	206.59	0.20%	✅
distilgpt2_fp16	16	2,094.87	2,092.89	0.09%	✅
yolov5s	1	552.78	558.33	-0.99%	✅
tinyllama	1	45.85	45.83	0.04%	✅
vicuna-fastchat	1	44.21	44.20	0.02%	✅
whisper-tiny-encoder	1	413.12	411.87	0.30%	✅
whisper-tiny-decoder	1	408.90	408.48	0.10%	✅
llama2_7b	1	20.83	20.84	-0.02%	✅
qwen1.5-7b	1	23.56	23.58	-0.10%	✅
phi3-3.8b	1	26.72	26.72	0.03%	✅
llama3-8b	1	21.77	21.80	-0.17%	✅
whisper-large-encoder	1	10.18	10.18	0.03%	✅
whisper-large-decoder	1	105.35	105.30	0.05%	✅
mistral-7b	1	23.77	23.78	-0.01%	✅
FLUX.1-schnell	1	771.00	755.22	2.09%	✅

Regressions detected 🔴

* No develop baseline was found for this PR's branch point; compared against the latest available develop run instead.

[gh-app-migraphx-bot-pr-write]

Test	Status	Result
bert-mrpc-onnx	✅	PASSED: MIGraphX meets tolerance
bert-mrpc-tf	✅	PASSED: MIGraphX meets tolerance
pytorch-examples-wlang-gru	✅	PASSED: MIGraphX meets tolerance
pytorch-examples-wlang-lstm	✅	PASSED: MIGraphX meets tolerance
dlrm-criteoterabyte	✅	PASSED: MIGraphX meets tolerance
agentmodel	✅	PASSED: MIGraphX meets tolerance
unet	✅	PASSED: MIGraphX meets tolerance
resnet50v1	✅	PASSED: MIGraphX meets tolerance
bert_base_cased_fp16	✅	PASSED: MIGraphX meets tolerance
bert_large_uncased_fp16	🔴	FAILED: MIGraphX is not within tolerance - check verbose output
bert_large	✅	PASSED: MIGraphX meets tolerance
yolov5s	✅	PASSED: MIGraphX meets tolerance
tinyllama	✅	PASSED: MIGraphX meets tolerance
vicuna-fastchat	✅	PASSED: MIGraphX meets tolerance
whisper-tiny-encoder	✅	PASSED: MIGraphX meets tolerance
whisper-tiny-decoder	✅	PASSED: MIGraphX meets tolerance
llama2_7b	✅	PASSED: MIGraphX meets tolerance
qwen1.5-7b	✅	PASSED: MIGraphX meets tolerance
phi3-3.8b	✅	PASSED: MIGraphX meets tolerance
llama3-8b	✅	PASSED: MIGraphX meets tolerance
whisper-large-encoder	✅	PASSED: MIGraphX meets tolerance
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance