~/bookmarks

William's Bookmark Library

/**/

wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

github.comSaved August 25, 20269 min

Preview of wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

wafer-ai · via GitHub

Summary

A curated resource list for GPU performance engineering, organized from CUDA fundamentals through kernel optimization, inference engines, and distributed serving.

Sources are limited to original papers, official specifications, and direct implementation work. Covers hardware-specific content for NVIDIA, AMD, TPU, and Trainium.

Topics

CUDA Programming Kernel Optimization Inference Engines Distributed Inference GPU Performance Engineering

View on GitHub All Bookmarks

William's Bookmark Library

/**/

wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

github.comSaved August 25, 20269 min

wafer-ai · via GitHub

Summary

A curated resource list for GPU performance engineering, organized from CUDA fundamentals through kernel optimization, inference engines, and distributed serving.

Sources are limited to original papers, official specifications, and direct implementation work. Covers hardware-specific content for NVIDIA, AMD, TPU, and Trainium.

Topics

CUDA Programming Kernel Optimization Inference Engines Distributed Inference GPU Performance Engineering

View on GitHub All Bookmarks

~/bookmarks

wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

Summary

Topics

Discover Similar Content

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

GitHub - gufo-org/gufo: Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

Discover Similar Content

wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

Summary

Topics

Discover Similar Content

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

GitHub - gufo-org/gufo: Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2