Path	Lines of Code
ai-ml/gke-a100-jax/kubernetes/job-patch.yaml	16
ai-ml/gke-a100-jax/kubernetes/job.yaml	28
ai-ml/gke-a100-jax/kubernetes/kustomization.yaml	78
ai-ml/gke-a100-jax/kubernetes/service.yaml	8
ai-ml/gke-a100-jax/train.py	43
ai-ml/gke-online-serving-single-gpu/src/client/tfserve_mnist_client.py	28
ai-ml/gke-online-serving-single-gpu/src/client/triton_mnist_client.py	33
ai-ml/gke-online-serving-single-gpu/src/gke-config/deployment-tfserve.yaml	53
ai-ml/gke-online-serving-single-gpu/src/gke-config/deployment-triton.yaml	55
ai-ml/gke-online-serving-single-gpu/src/gke-config/service-tfserve.yaml	17
ai-ml/gke-online-serving-single-gpu/src/gke-config/service-triton.yaml	20
ai-ml/gke-ray/gke-platform/main.tf	72
ai-ml/gke-ray/gke-platform/modules/gke_autopilot/main.tf	29
ai-ml/gke-ray/gke-platform/modules/gke_autopilot/output.tf	20
ai-ml/gke-ray/gke-platform/modules/gke_autopilot/variables.tf	36
ai-ml/gke-ray/gke-platform/modules/gke_autopilot/versions.tf	7
ai-ml/gke-ray/gke-platform/modules/gke_standard/main.tf	124
ai-ml/gke-ray/gke-platform/modules/gke_standard/output.tf	20
ai-ml/gke-ray/gke-platform/modules/gke_standard/variables.tf	56
ai-ml/gke-ray/gke-platform/modules/gke_standard/versions.tf	7
ai-ml/gke-ray/gke-platform/modules/kuberay/kuberay-operator-autopilot-values.yaml	33
ai-ml/gke-ray/gke-platform/modules/kuberay/kuberay-operator-values.yaml	31
ai-ml/gke-ray/gke-platform/modules/kuberay/kuberay.tf	13
ai-ml/gke-ray/gke-platform/modules/kuberay/variables.tf	20
ai-ml/gke-ray/gke-platform/modules/kuberay/versions.tf	15
ai-ml/gke-ray/gke-platform/modules/kubernetes/kubernetes.tf	7
ai-ml/gke-ray/gke-platform/modules/kubernetes/variables.tf	25
ai-ml/gke-ray/gke-platform/modules/kubernetes/versions.tf	19
ai-ml/gke-ray/gke-platform/variables.tf	47
ai-ml/gke-ray/gke-platform/versions.tf	26
ai-ml/gke-ray/rayserve/ap_falcon-40b.yaml	107
ai-ml/gke-ray/rayserve/ap_falcon-7b.yaml	90
ai-ml/gke-ray/rayserve/ap_llama2-70b.yaml	107
ai-ml/gke-ray/rayserve/ap_llama2-7b.yaml	96
ai-ml/gke-ray/rayserve/ap_pvc-rayservice.yaml	11
ai-ml/gke-ray/rayserve/falcon-40b.yaml	97
ai-ml/gke-ray/rayserve/falcon-7b.yaml	85
ai-ml/gke-ray/rayserve/gradio.yaml	41
ai-ml/gke-ray/rayserve/ingress/gateway.yaml	10
ai-ml/gke-ray/rayserve/ingress/healthcheckpolicy.yaml	21
ai-ml/gke-ray/rayserve/ingress/httproute.yaml	12
ai-ml/gke-ray/rayserve/llama2-70b.yaml	97
ai-ml/gke-ray/rayserve/llama2-7b.yaml	91
ai-ml/gke-ray/rayserve/llm/gemma-2b-it/ray-service.yaml	87
ai-ml/gke-ray/rayserve/llm/gemma-7b-it/ray-service.yaml	86
ai-ml/gke-ray/rayserve/llm/llama-2-7b/gradio.yaml	48
ai-ml/gke-ray/rayserve/llm/llama-2-7b/ray-service.yaml	86
ai-ml/gke-ray/rayserve/llm/llama-3-8b/gradio.yaml	48
ai-ml/gke-ray/rayserve/llm/llama-3-8b/ray-service.yaml	86
ai-ml/gke-ray/rayserve/llm/mistral-7b/ray-service.yaml	86
ai-ml/gke-ray/rayserve/llm/model-composition/ray-service.tpu-v5e-singlehost.yaml	132
ai-ml/gke-ray/rayserve/llm/model-composition/ray-service.tpu-v6e-singlehost.yaml	132
ai-ml/gke-ray/rayserve/llm/model-composition/ray-service.yaml	86
ai-ml/gke-ray/rayserve/llm/model-composition/serve.py	94
ai-ml/gke-ray/rayserve/llm/model-composition/serve_tpu.py	129
ai-ml/gke-ray/rayserve/llm/model-multiplexing/ray-service.yaml	88
ai-ml/gke-ray/rayserve/llm/model-multiplexing/serve.py	76
ai-ml/gke-ray/rayserve/llm/serve.py	57
ai-ml/gke-ray/rayserve/llm/serve_chat_completion.py	87
ai-ml/gke-ray/rayserve/llm/tpu/ray-cluster.tpu-v5e-singlehost.yaml	126
ai-ml/gke-ray/rayserve/llm/tpu/ray-cluster.tpu-v6e-singlehost.yaml	126
ai-ml/gke-ray/rayserve/llm/tpu/ray-service.tpu-v5e-singlehost.yaml	140
ai-ml/gke-ray/rayserve/llm/tpu/ray-service.tpu-v6e-singlehost.yaml	140
ai-ml/gke-ray/rayserve/llm/tpu/serve_tpu.py	87
ai-ml/gke-ray/rayserve/models/falcon-7b-instruct.yaml	47
ai-ml/gke-ray/rayserve/models/llama2-7b-chat-hf.yaml	47
ai-ml/gke-ray/rayserve/models/quantized-model.yaml	66
ai-ml/gke-ray/rayserve/stable-diffusion/generate_image.py	8
ai-ml/gke-ray/rayserve/stable-diffusion/ray-cluster.yaml	58
ai-ml/gke-ray/rayserve/stable-diffusion/ray-service-tpu.yaml	68
ai-ml/gke-ray/rayserve/stable-diffusion/ray-service.yaml	65
ai-ml/gke-ray/rayserve/stable-diffusion/stable_diffusion.py	44
ai-ml/gke-ray/rayserve/stable-diffusion/stable_diffusion_tpu.py	95
ai-ml/gke-ray/rayserve/stable-diffusion/stable_diffusion_tpu_req.py	113
ai-ml/gke-ray/raytrain/pytorch-mnist/ray-cluster.yaml	51
ai-ml/gke-ray/raytrain/pytorch-mnist/ray-job.yaml	60
ai-ml/gke-ray/raytrain/pytorch-mnist/train.py	104
ai-ml/llm-finetuning-gemma/cloudbuild.yaml	5
ai-ml/llm-finetuning-gemma/finetune.py	129
ai-ml/llm-finetuning-gemma/finetune.yaml	55
ai-ml/llm-multihost-gpus/vllm-llama3-405b-A3-HDML.yaml	95
ai-ml/llm-multihost-gpus/vllm-llama3-405b-A3.yaml	91
ai-ml/llm-multihost-tpus-saxml/sax-admin-server.yaml	26
ai-ml/llm-multihost-tpus-saxml/sax-http.yaml	37
ai-ml/llm-multihost-tpus-saxml/sax-model-server-set.yaml	44
ai-ml/llm-multiple-gpus/falcon-40b/gradio.yaml	55
ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml	59
ai-ml/llm-multiple-gpus/llama2-70b/gradio.yaml	55
ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml	64
ai-ml/llm-multiple-gpus/llama3-70b/gradio.yaml	55
ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml	66
ai-ml/llm-multiple-gpus/llm-service.yaml	12
ai-ml/llm-multiple-gpus/mixtral-8x7b/gradio.yaml	55
ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml	64
ai-ml/llm-serving-gemma/gradio/app/app.py	112
ai-ml/llm-serving-gemma/gradio/cloudbuild.yaml	13
ai-ml/llm-serving-gemma/saxml/job-2b.yaml	57
ai-ml/llm-serving-gemma/saxml/job-7b.yaml	57
ai-ml/llm-serving-gemma/saxml/saxml-admin-server.yaml	25
ai-ml/llm-serving-gemma/saxml/saxml-http.yaml	37
ai-ml/llm-serving-gemma/saxml/saxml-model-server-1x1.yaml	45
ai-ml/llm-serving-gemma/saxml/saxml-model-server-2x2.yaml	45
ai-ml/llm-serving-gemma/tgi/gradio.yaml	54
ai-ml/llm-serving-gemma/tgi/tgi-1_1-2b-it.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-1_1-7b-it.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-2-27b-it.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2-27b.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2-2b-it.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2-2b.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2-9b-it.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2-9b.yaml	73
ai-ml/llm-serving-gemma/tgi/tgi-2b-bitsandbytes-nf4/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-2b-bitsandbytes-nf4/patch.yaml	16
ai-ml/llm-serving-gemma/tgi/tgi-2b-bitsandbytes/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-2b-bitsandbytes/patch.yaml	16
ai-ml/llm-serving-gemma/tgi/tgi-2b-it-a100-40gb.yaml	62
ai-ml/llm-serving-gemma/tgi/tgi-2b-it-a100-80gb.yaml	62
ai-ml/llm-serving-gemma/tgi/tgi-2b-it-h100-80gb.yaml	63
ai-ml/llm-serving-gemma/tgi/tgi-2b-it.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-2b-parallel/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-2b-parallel/patch.yaml	15
ai-ml/llm-serving-gemma/tgi/tgi-2b.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes-nf4.yaml	67
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes-nf4/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes-nf4/patch.yaml	16
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes.yaml	67
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-7b-bitsandbytes/patch.yaml	16
ai-ml/llm-serving-gemma/tgi/tgi-7b-it-a100-40gb.yaml	62
ai-ml/llm-serving-gemma/tgi/tgi-7b-it-a100-80gb.yaml	62
ai-ml/llm-serving-gemma/tgi/tgi-7b-it-h100-80gb.yaml	63
ai-ml/llm-serving-gemma/tgi/tgi-7b-it-tensorparallelism.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-7b-it.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-7b-token.yaml	69
ai-ml/llm-serving-gemma/tgi/tgi-7b-token/kustomization.yaml	11
ai-ml/llm-serving-gemma/tgi/tgi-7b-token/patch.yaml	21
ai-ml/llm-serving-gemma/tgi/tgi-7b.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-codegemma-1.1-2b.yaml	66
ai-ml/llm-serving-gemma/tgi/tgi-codegemma-1.1-7b-it.yaml	66
ai-ml/llm-serving-gemma/trtllm/deploy-triton-server.yaml	115
ai-ml/llm-serving-gemma/trtllm/job-download-gemma-2b.yaml	80
ai-ml/llm-serving-gemma/trtllm/job-download-gemma-7b.yaml	79
ai-ml/llm-serving-gemma/trtllm/trtllm_checkpoint_pv.yaml	10
ai-ml/llm-serving-gemma/vllm/gradio.yaml	54
ai-ml/llm-serving-gemma/vllm/vllm-1_1-2b.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-1_1-7b.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-2-27b-it.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2-27b.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2-2b-it.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2-2b.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2-9b-it.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2-9b.yaml	66
ai-ml/llm-serving-gemma/vllm/vllm-2b-awq/kustomization.yaml	11
ai-ml/llm-serving-gemma/vllm/vllm-2b-awq/patch.yaml	19
ai-ml/llm-serving-gemma/vllm/vllm-2b-it-a100-40gb.yaml	61
ai-ml/llm-serving-gemma/vllm/vllm-2b-it-a100-80gb.yaml	61
ai-ml/llm-serving-gemma/vllm/vllm-2b-it-h100-80gb.yaml	62
ai-ml/llm-serving-gemma/vllm/vllm-2b-it.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-2b-parallel/kustomization.yaml	11
ai-ml/llm-serving-gemma/vllm/vllm-2b-parallel/patch.yaml	15
ai-ml/llm-serving-gemma/vllm/vllm-2b.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-7b-awq.yaml	69
ai-ml/llm-serving-gemma/vllm/vllm-7b-awq/kustomization.yaml	11
ai-ml/llm-serving-gemma/vllm/vllm-7b-awq/patch.yaml	24
ai-ml/llm-serving-gemma/vllm/vllm-7b-it-a100-40gb.yaml	61
ai-ml/llm-serving-gemma/vllm/vllm-7b-it-a100-80gb.yaml	61
ai-ml/llm-serving-gemma/vllm/vllm-7b-it-h100-80gb.yaml	62
ai-ml/llm-serving-gemma/vllm/vllm-7b-it-tensorparallelism.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-7b-it.yaml	65
ai-ml/llm-serving-gemma/vllm/vllm-7b-kvcache.yaml	70
ai-ml/llm-serving-gemma/vllm/vllm-7b-kvcache/kustomization.yaml	11
ai-ml/llm-serving-gemma/vllm/vllm-7b-kvcache/patch.yaml	28
ai-ml/llm-serving-gemma/vllm/vllm-7b-token.yaml	69
ai-ml/llm-serving-gemma/vllm/vllm-7b-token/kustomization.yaml	11
ai-ml/llm-serving-gemma/vllm/vllm-7b-token/patch.yaml	27
ai-ml/llm-serving-gemma/vllm/vllm-7b.yaml	65
ai-ml/llm-serving-optimum-tpu/optimum-tpu-gemma-2b-2x4.yaml	58
ai-ml/llm-serving-optimum-tpu/optimum-tpu-llama3-8b-2x4.yaml	56
ai-ml/llm-serving-tpus-jetstream/pytorch/jetstream-pytorch-gemma-7b-it-2x4.yaml	93
ai-ml/llm-serving-tpus-jetstream/pytorch/jetstream-pytorch-llama-3-8b-2x4.yaml	93
ai-ml/llm-serving-tpus-jetstream/pytorch/job-gemma-7b-it.yaml	36
ai-ml/llm-serving-tpus-jetstream/pytorch/job-llama-3-8b.yaml	36
ai-ml/maxdiffusion-tpu/build/server/cloudbuild.yaml	5
ai-ml/maxdiffusion-tpu/build/server/main.py	154
ai-ml/maxdiffusion-tpu/build/webapp/app.py	22
ai-ml/maxdiffusion-tpu/build/webapp/cloudbuild.yaml	5
ai-ml/maxdiffusion-tpu/serve_sdxl_client.yaml	40
ai-ml/maxdiffusion-tpu/serve_sdxl_v5e.yaml	53
ai-ml/maxdiffusion-tpu/serve_sdxl_v6e.yaml	61
ai-ml/mix-train-and-inference/gke-platform/main.tf	56
ai-ml/mix-train-and-inference/gke-platform/modules/gke_autopilot/main.tf	58
ai-ml/mix-train-and-inference/gke-platform/modules/gke_autopilot/output.tf	20
ai-ml/mix-train-and-inference/gke-platform/modules/gke_autopilot/variables.tf	42
ai-ml/mix-train-and-inference/gke-platform/modules/gke_standard/main.tf	152
ai-ml/mix-train-and-inference/gke-platform/modules/gke_standard/output.tf	20
ai-ml/mix-train-and-inference/gke-platform/modules/gke_standard/variables.tf	67
ai-ml/mix-train-and-inference/gke-platform/variables.tf	68
ai-ml/mix-train-and-inference/gke-platform/versions.tf	12
ai-ml/mix-train-and-inference/kueue/kustomization.yaml	10
ai-ml/mix-train-and-inference/kueue/patch.yaml	52
ai-ml/mix-train-and-inference/workloads/cluster-queue.yaml	22
ai-ml/mix-train-and-inference/workloads/default-priorityclass.yaml	8
ai-ml/mix-train-and-inference/workloads/fine-tune-l4.yaml	99
ai-ml/mix-train-and-inference/workloads/flavors.yaml	4
ai-ml/mix-train-and-inference/workloads/high-priorityclass.yaml	8
ai-ml/mix-train-and-inference/workloads/local-queue.yaml	7
ai-ml/mix-train-and-inference/workloads/low-priorityclass.yaml	8
ai-ml/mix-train-and-inference/workloads/tgi-gemma-2-9b-it-hp.yaml	70
ai-ml/t5-model-serving/client-app/cloudbuild.yaml	10
ai-ml/t5-model-serving/client-app/src/app.py	34
ai-ml/t5-model-serving/client-app/src/wsgi.py	2
ai-ml/t5-model-serving/kubernetes/application.yaml	56
ai-ml/t5-model-serving/kubernetes/hpa.yaml	19
ai-ml/t5-model-serving/kubernetes/loadgenerator.yaml	99
ai-ml/t5-model-serving/kubernetes/pod-monitoring.yaml	15
ai-ml/t5-model-serving/kubernetes/serving-cpu.yaml	85
ai-ml/t5-model-serving/kubernetes/serving-gpu.yaml	89
ai-ml/t5-model-serving/loadgenerator/locustfile.py	20
ai-ml/t5-model-serving/model/cloudbuild.yaml	29
ai-ml/t5-model-serving/model/handler.py	68
ai-ml/t5-model-serving/model/model.py	1
ai-ml/vllm-tpu/vllm-hpa.yaml	19
ai-ml/vllm-tpu/vllm-llama3-70b.yaml	84
ai-ml/vllm-tpu/vllm_pod_monitor.yaml	12