llm 111 gpu 87 kubernetes 87 deep-learning 77 pytorch 76 ai 61 machine-learning 57 transformer 48 vllm 43 nvidia 36 python 29 quantization 25 tensorrt 23 transformers 21 onnx 21 cuda 21 large-language-models 21 tensorflow 20 cloud-functions 20 serverless-gpu 20 openai 19 go 18 ai-gateway 18 sglang 18 openvino 18 operator 17 training 17 agentic 17 llm-serving 17 llama 17 leader-worker 16 model-serving 16 llmops 16 grove 16 topology-aware-scheduling 16 multinode 16 golang 16 llm-inference 16 role-based 16 gang-scheduling 16 disaggregated 16 auto-scaling 16 auto-scaling-group 16 llama-cpp 16 llms 15 mlops 14 nlp 13 reinforcement-learning 12 qwen 12 semantic-router 12 inference-engine 12 mixture-of-models 12 llmrouter 12 self-hosted 12 guardrails 12 local-llm 11 computer-vision 11 generative-ai 11 speech-recognition 11 huggingface 11 openapi 10 openai-api 10 cli 10 api 10 grpc 10 pipeline-parallelism 10 local-ai 10 kv-cache 10 whisper 10 onnxruntime 10 reasoning 10 cpp 10 logic 9 docker 9 edge 9 gguf 9 ai-agents 9 speech-to-text 9 serving 9 data-parallelism 9 model-parallelism 9 neural-network 9 fine-tuning 8 gpt 8 translation 8 compression 8 ollama 8 tensorflow-lite 8 mcp 8 macos 8 rdma 8 gpu-acceleration 8 open-source 8 tui 8 autoscaling 8 agentic-ai 8 k8s 7 disaggregation 7 tokenspeed 7 kvcache 7