Add GroupQueryAttention with KV-Cache

[turneram]

No description provided.

[migraphx-bot]

Test	Batch	Rate new 725f34	Rate old a1e339	Diff	Compare
torchvision-resnet50	64	3,260.60	3,261.15	-0.02%	✅
torchvision-resnet50_fp16	64	6,985.29	6,998.48	-0.19%	✅
torchvision-densenet121	32	2,438.58	2,437.74	0.03%	✅
torchvision-densenet121_fp16	32	4,107.52	4,082.54	0.61%	✅
torchvision-inceptionv3	32	1,639.29	1,637.99	0.08%	✅
torchvision-inceptionv3_fp16	32	2,762.34	2,759.69	0.10%	✅
cadene-inceptionv4	16	776.94	777.37	-0.05%	✅
cadene-resnext64x4	16	810.02	809.89	0.02%	✅
slim-mobilenet	64	7,535.95	7,538.41	-0.03%	✅
slim-nasnetalarge	64	211.84	211.83	0.01%	✅
slim-resnet50v2	64	3,504.66	3,505.62	-0.03%	✅
bert-mrpc-onnx	8	1,148.36	1,153.97	-0.49%	✅
bert-mrpc-tf	1	465.22	463.62	0.35%	✅
pytorch-examples-wlang-gru	1	423.64	416.54	1.71%	✅
pytorch-examples-wlang-lstm	1	474.21	375.99	26.12%	🔆
torchvision-resnet50_1	1	783.58	787.35	-0.48%	✅
cadene-dpn92_1	1	400.96	398.81	0.54%	✅
cadene-resnext101_1	1	384.06	382.80	0.33%	✅
onnx-taau-downsample	1	342.41	342.52	-0.03%	✅
dlrm-criteoterabyte	1	33.33	33.35	-0.07%	✅
dlrm-criteoterabyte_fp16	1	52.77	52.52	0.49%	✅
agentmodel	1	10,167.28	8,468.76	20.06%	🔆
unet_fp16	2	58.94	58.99	-0.08%	✅
resnet50v1_fp16	1	953.52	916.35	4.06%	🔆
resnet50v1_int8	1	980.77	972.58	0.84%	✅
bert_base_cased_fp16	64	1,172.32	1,170.84	0.13%	✅
bert_large_uncased_fp16	32	363.60	363.63	-0.01%	✅
bert_large_fp16	1	201.32	199.03	1.15%	✅
distilgpt2_fp16	16	2,204.29	2,203.30	0.05%	✅
yolov5s	1	531.15	528.92	0.42%	✅
tinyllama	1	43.42	43.76	-0.78%	✅
vicuna-fastchat	1	171.63	173.75	-1.22%	✅
whisper-tiny-encoder	1	417.81	418.39	-0.14%	✅
whisper-tiny-decoder	1	427.35	427.20	0.04%	✅

Check results before merge 🔆

[migraphx-bot]

     ✅ 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

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: 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

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance