harvard-edge/cs249r_book
Harvard CS249r open textbook series on machine learning systems, with labs, TinyTorch, and hardware kits.
As of Oct 22, 2026, harvard-edge/cs249r_book has 29,112 GitHub stars, +26 since Oct 21, 2026, #50 among Model & inference repos this week.
- Total stars
- 29,112
- Last day
- +26
- Since Oct 21, 2026
- +26
- Weekly rank
- #387
- Category
- Model & inference repos
- Language
- Python
Daily history starts Oct 22, 2026.
Links
cs249r_book alternatives in Model & inference repos
- deepseek-ai/DeepInfer · 18,843 ★ · +3,838 /7dOpen-source offline inference framework for DeepSeek models with optimized kernels, parallelism, and scheduling.
- Comfy-Org/ComfyUI · 141,762 ★ · +769 /7dNode-based GUI and backend that runs diffusion models locally for image, video, audio and 3D generation.
- Niko1221/Strata · 30,133 ★ · +744 /7dStrata is a local inference engine running Qwen3.8-Flash-Next on consumer hardware.
- tashfeenahmed/freellmapi · 39,146 ★ · +674 /7dAggregates free tiers from 34 LLM providers into one OpenAI-compatible endpoint with routing and failover.
- Fractal-Compute-Orchestrations/FractalWorkspace · 3,101 ★ · +671 /7dA distributed framework for federated learning and edge model training across Android and Python nodes.
- Fractal-Compute-Orchestrations/FractalAndroid · 3,010 ★ · +666 /7dAndroid edge compute client running on-device federated learning and distributed ML workloads.
- headroomlabs-ai/headroom · 77,434 ★ · +564 /7dCompresses tool outputs, logs, files, and RAG chunks locally before they reach the LLM, reducing token usage.
- vllm-project/vllm · 95,038 ★ · +501 /7dvLLM is a high-throughput, memory-efficient open-source engine for LLM inference and serving.
Badge for your README
Data: daily star-total snapshots from the GitHub GraphQL API; stars gained = difference between snapshots. GitHub search and GH Archive are used to find repos. Updated daily around 02:30 UTC, counting through the last complete UTC day. · By Kai
How we rank · Weekly archive · RSS · JSON API