--- id: "/infrastructure-chips-efficiency/advanced/page/2/" title: "Infrastructure, chips & efficiency for advanced learners · page 2" url: "https://skillissue.dev/infrastructure-chips-efficiency/advanced/page/2/" --- # Infrastructure, chips & efficiency for advanced learners [Beginner](/infrastructure-chips-efficiency/beginner/index.md) [Intermediate](/infrastructure-chips-efficiency/intermediate/index.md) [Advanced](/infrastructure-chips-efficiency/advanced/index.md) [Expert](/infrastructure-chips-efficiency/expert/index.md) 86 resources · page 2 of 3 - ### [NVIDIA Dynamo](/model-training/training-infrastructure/nvidia-dynamo/index.md) by [Dynamo](https://developer.nvidia.com/dynamo) ai-dynamo Dynamo GitHub repo: NVIDIA's datacenter-scale distributed, disaggregated inference serving framework. entity repo US en - ### [NVIDIA NeMo Speech](/model-training/training-infrastructure/nvidia-nemo-speech/index.md) by [NVIDIA-NeMo](https://nvidia.com/) NVIDIA NeMo Speech GitHub repo: framework for speech recognition and TTS model training and inference. entity repo US en - ### [NVIDIA/TensorRT-LLM](/model-training/training-infrastructure/nvidia-tensorrt-llm/index.md) by [NVIDIA Corporation](https://nvidia.com) NVIDIA TensorRT-LLM GitHub repo: Python API and kernels for optimised LLM inference on NVIDIA GPUs. entity repo US en - ### [NVIDIA VerilogEval](/model-training/training-infrastructure/nvidia-verilogeval/index.md) by [NVIDIA Research Projects](https://research.nvidia.com/) NVIDIA VerilogEval GitHub repo: benchmark for evaluating LLMs on generating Verilog hardware-description code. entity benchmark US en - ### [Ollama](/model-training/training-infrastructure/ollama-repo/index.md) by [Ollama](https://ollama.com) Ollama GitHub repo: runtime for running open LLMs locally, with API and cloud options. entity repo US en - ### [OLMo training and inference](/model-training/training-infrastructure/olmo-training-and-inference/index.md) by [Ai2](https://allenai.org/) Ai2 OLMo GitHub repo: modelling, training, evaluation and inference code for OLMo open language models. entity repo US en - ### [OpenROAD](/model-training/training-infrastructure/openroad/index.md) by [The OpenROAD Project](https://theopenroadproject.org/) OpenROAD GitHub repo: open RTL-to-GDS chip design flow, also used in ML-for-EDA research. entity repo US en - ### [SageAttention](/model-training/training-infrastructure/sageattention/index.md) by [TSAIL group](https://ml.cs.tsinghua.edu.cn) Tsinghua SageAttention GitHub repo: quantised low-bit attention kernels for faster inference. entity repo China en - ### [onediff](/model-training/training-infrastructure/siliconflow-onediff/index.md) by [SiliconFlow](https://siliconflow.com) SiliconFlow onediff GitHub repo: acceleration library for diffusion model inference. entity repo China en|zh - ### [Tenstorrent](/model-training/training-infrastructure/tenstorrent/index.md) by [Tenstorrent](https://tenstorrent.com/) Tenstorrent: company building RISC-V based AI accelerators and computers. entity lab US en - ### [ThunderKittens](/model-training/training-infrastructure/thunderkittens/index.md) by [HazyResearch](https://cs.stanford.edu/people/chrismre/) HazyResearch ThunderKittens GitHub repo: tile primitives framework for writing fast GPU kernels. entity repo US en - ### [TileKernels](/model-training/training-infrastructure/tilekernels/index.md) by [DeepSeek](https://www.deepseek.com/) DeepSeek TileKernels GitHub repo: library of GPU kernels written in TileLang. entity repo China en - ### [Together cookbook](/model-training/training-infrastructure/together-cookbook/index.md) by [Together](https://github.com/togethercomputer) Together cookbook GitHub repo: notebooks with recipes for building with Together AI models. entity repo US en - ### [torchtitan](/model-training/training-infrastructure/torchtitan/index.md) by [pytorch](https://pytorch.org) PyTorch torchtitan GitHub repo: PyTorch-native platform for large-scale generative model pretraining. entity repo US en - ### [fairseq: NLLB branch](/model-training/training-infrastructure/translation-localization/index.md) by [Meta Research](https://opensource.fb.com) Meta fairseq nllb branch on GitHub: code for the No Language Left Behind translation models. entity repo US en - ### [Triton-distributed](/model-training/training-infrastructure/triton-distributed/index.md) by [ByteDance-Seed](https://seed.bytedance.com/) ByteDance Seed Triton-distributed GitHub repo: distributed compiler and parallel kernels overlapping compute and communication. entity repo China en - ### [TurboDiffusion (thu-ml)](/model-training/training-infrastructure/turbodiffusion-thu-ml/index.md) by [TSAIL group](https://ml.cs.tsinghua.edu.cn) Tsinghua TurboDiffusion GitHub repo: acceleration framework for video diffusion models. entity repo China en - ### [GPU Glossary (Modal)](/model-training/training-infrastructure/modal-gpu-glossary/index.md) by [Modal](https://modal.com/) Modal GPU Glossary: reference explaining GPU hardware and software terms from CUDA cores to memory hierarchy. Beginner–Expert learning_resource guide US en - ### [AMD ROCm](/model-training/training-infrastructure/amd-rocm/index.md) by [AMD](https://amd.com/) AMD ROCm developer hub with documentation, training and tools for GPU-accelerated computing on AMD hardware. Intermediate–Advanced learning_resource docs US en - ### [Google TPU docs](/model-training/training-infrastructure/google-tpu-docs/index.md) by [Google Cloud](https://cloud.google.com/) Google Cloud TPU documentation for running machine-learning training and inference on Tensor Processing Units. Intermediate–Advanced learning_resource docs US en - ### [GPU MODE](/model-training/training-infrastructure/gpu-mode/index.md) by [GPU MODE community](https://www.gpumode.com/) GPU MODE site: community for learning GPU programming through lectures, hackathons, kernel competitions and working groups. Intermediate–Advanced learning_resource course Global en - ### [GPU MODE lectures](/model-training/training-infrastructure/gpu-mode-lectures/index.md) by [GPU MODE](https://github.com/gpu-mode) GPU MODE lectures GitHub repo: slides and code from community lectures on GPU programming and CUDA kernels. Intermediate–Advanced learning_resource course Global en - ### [vLLM documentation](/model-training/training-infrastructure/inference-serving-quantization/index.md) by [vLLM project](https://vllm.ai/) vLLM documentation: open-source engine for high-throughput LLM inference and serving. Intermediate–Advanced learning_resource docs US en - ### [PyTorch FSDP tutorial](/model-training/training-infrastructure/pytorch-fsdp-tutorial/index.md) by [PyTorch Foundation](https://pytorch.org/) PyTorch tutorial on Fully Sharded Data Parallel (FSDP2) for training large models across GPUs. Intermediate–Advanced learning_resource docs US en - ### [SGLang documentation](/model-training/training-infrastructure/sglang/index.md) by [SGLang project (LMSYS)](https://lmsys.org/) SGLang documentation: serving framework for large language and multimodal models. Intermediate–Advanced learning_resource docs US en - ### [Triton tutorials](/model-training/training-infrastructure/triton-tutorials/index.md) by [OpenAI (Triton)](https://triton-lang.org/) Triton tutorials: ordered examples from vector addition to fused softmax, matmul and fused attention GPU kernels. Intermediate–Advanced learning_resource docs US en - ### [A graph placement methodology for fast chip design](/model-training/training-infrastructure/alphachip-mirhoseini-et-al-nature-2021/index.md) by [Azalia Mirhoseini et al. (Google)](https://ai.google/) Nature paper (2021) by Mirhoseini et al. introducing the reinforcement learning chip floorplanning method later named AlphaChip. Advanced learning_resource paper US en - ### [Agentic inference optimization (Baseten)](/model-training/training-infrastructure/baseten-agentic-inference-optimization/index.md) by [Baseten](https://baseten.co/) Baseten post on optimising inference engines for agent workloads, reporting decode-speed and latency gains over vLLM. Advanced learning_resource blog US en - ### [Baseten documentation](/model-training/training-infrastructure/baseten-documentation/index.md) by [Baseten](https://www.baseten.co/) Baseten documentation for running hosted models, deploying custom models and training on GPU infrastructure. Advanced learning_resource docs US en - ### [BentoML documentation](/model-training/training-infrastructure/bentoml-documentation/index.md) by [BentoML](https://www.bentoml.com/) BentoML documentation: open-source inference platform for packaging, deploying and scaling AI models. Advanced learning_resource docs US/global en - ### [Code execution with MCP](/model-training/training-infrastructure/code-execution-with-mcp/index.md) by [Anthropic](https://anthropic.com/) Anthropic post on code execution with MCP: agents write code to call tools, reducing token use and context load. Advanced learning_resource guide US en - ### [Defeating Nondeterminism in LLM Inference](/model-training/training-infrastructure/defeating-nondeterminism-in-llm-inference/index.md) by [Thinking Machines Lab](https://thinkingmachines.ai/) Thinking Machines Lab post on the causes of nondeterminism in LLM inference and batch-invariant kernels to fix it. Advanced learning_resource paper US en [Previous page](/infrastructure-chips-efficiency/advanced/index.md) [Next page](/infrastructure-chips-efficiency/advanced/page/3/index.md) [Plain-text Markdown copy](/infrastructure-chips-efficiency/advanced/page/2/index.md)