# gpu-mode/awesomeMLSys

An ML Systems Onboarding list

Repository: https://github.com/gpu-mode/awesomeMLSys
Canonical: https://ross.abutalabs.com/products/awesomemlsys
License Family: other
Last push: 2026-02-19T06:25:40+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 68, release rhythm 35, longevity 60
- inputs: {"age_days": 849, "days_push": 195, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1120, forks 45 (observed 2026-08-28T04:03:39.709203+00:00)

## What it is
A curated reading list of papers, videos, and repositories for onboarding into ML Systems, covering attention mechanisms, LLM inference, and performance optimizations. It is maintained by the GPU Mode community and points to resources like Flash Attention, PagedAttention, and speculative decoding.

## Use cases
- learn ml systems fundamentals
- find papers on llm inference optimization
- understand flash attention and kv caches
- onboarding material for gpu inference engineering
- study list for transformer serving performance
- learn about paged attention and continuous batching

## When to choose
- you are ramping up on ML systems and LLM inference
- you want a curated, opinionated study path with papers and repos
- you want to understand GPU-level performance optimizations for transformers

## When to avoid
- you need runnable software rather than a reading list
- you want beginner-level machine learning tutorials unrelated to systems
- you need exhaustive coverage of all ML topics

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, gpu-computing, machine-learning
- domain: machine-learning, large-language-models, gpu-computing, tutorials
- platform: python
- tags: reading-list, ml-systems, awesome-list, papers, inference-optimization, gpu

## Member repositories
- gpu-mode/awesomeMLSys (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:39.709203+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:05.894342+00:00, confidence not recorded.
  - readme: https://github.com/gpu-mode/awesomeMLSys (fetched 2026-08-28T04:03:39.709203+00:00, sha c8f1805ace76)
- Data as of 2026-08-30T08:39:29.467469+00:00.