Infrastructure, chips & efficiency for advanced learners
86 resources · page 3 of 3
DoWhy documentation
by PyWhy
DoWhy documentation: Python library for causal inference with modelling, identification, estimation and refutation steps.
EconML
by PyWhy
EconML documentation: Python methods for estimating heterogeneous treatment effects with machine learning.
Feast documentation
Feast documentation: open-source feature store for serving consistent features to ML training and inference.
Fireworks AI documentation
by Fireworks AI
Fireworks AI documentation: serverless and dedicated inference, fine-tuning and deployment of open models.
Three Tests to Run Before You Switch from LoRA to FullFT (Fireworks AI)
by Fireworks AI
Fireworks AI post with controlled experiments on Qwen3.5-9B showing what to test before switching from LoRA to full fine-tuning.
Building an efficient harness for advanced enterprise work (Glean)
by Glean
Glean post on its coding-agent harness using code execution, tool-output truncation and progressive disclosure to cut tokens.
Grouped-Query Attention
by Joshua Ainslie et al. (Google)
arXiv paper (2023) introducing grouped-query attention (GQA) and uptraining multi-head models to it.
MindSpore 中文 API 文档
MindSpore API documentation in Chinese for Huawei's deep learning training and inference framework.
Modal guides
by Modal
Modal guides: deploying model serving, GPU jobs and scalable applications on Modal's serverless platform.
Scaling to 1 million concurrent sandboxes in seconds (Modal)
by Modal
Modal engineering post on building a scheduler that runs one million concurrent code sandboxes per workspace.
Moore Threads docs center
Moore Threads documentation centre for its Chinese GPUs and the MUSA SDK (in Chinese).
PEFT documentation
by Hugging Face
Hugging Face PEFT documentation: parameter-efficient fine-tuning methods such as LoRA, with recipes.
Qiskit Machine Learning
Qiskit Machine Learning documentation: quantum kernels and quantum neural networks for ML experiments.
QLoRA
by Tim Dettmers et al. (University of Washington)
arXiv paper (2023) introducing QLoRA, fine-tuning 4-bit quantized LLMs with low-rank adapters.
Ray Serve documentation
Ray Serve documentation: scalable library for building online inference APIs and composing model deployments.
SGLang docs: HiCache best practices
by sgl-project
SGLang HiCache best practices: configuring hierarchical KV caching across GPU, CPU and storage.
Tinker documentation
Tinker documentation from Thinking Machines Lab: training API for fine-tuning open-weight LLMs, with SDK reference and recipes.
AdapTive-LeArning Speculator System (ATLAS) (Together AI)
by Together AI
Together AI post on ATLAS, a speculative decoding system whose speculators keep learning from the live workload.
Cache-aware prefill-decode disaggregation (Together AI)
by Together AI
Together AI post on cache-aware prefill-decode disaggregation for faster long-context inference serving.
Together AI documentation
by Together AI
Together AI documentation for running, fine-tuning and serving open-source models.
vLLM docs: Automatic prefix caching
by vLLM
vLLM design document on automatic prefix caching and how shared prompt prefixes reuse the KV cache.
vLLM docs
by vLLM project
vLLM latest documentation: installation, serving, supported models and quantisation for the LLM inference engine.