Replace 9 old tutorials with 12 new numbered tutorials (00-11) covering
roofline through full-stack audit. Redesign landing page, add
models-and-solvers and extending-the-engine guides. Add __main__.py,
cli.py, and cli/ package for command-line interface.
Add cached_prefix_len parameter to ServingSolver for prefix/prompt
caching (grounded in Zheng et al. SGLang/RadixAttention). TTFT reduces
proportionally to cache hit ratio; ITL and memory unchanged.
Export 4 missing solvers from __init__.py (ContinuousBatchingSolver,
WeightStreamingSolver, TailLatencySolver, CheckpointSolver).
Fix dict-style access in for-engineers.qmd and architecture_comparison
tutorial. Add math sections 3.4-3.6 for prompt caching, disaggregated
serving (Patel et al. Splitwise ISCA'24), and speculative decoding
(Leviathan et al. ICML'23) with literature citations. Update paper.tex
Wall 4 description to include prompt caching. Fix remaining MLSYSIM
branding in _quarto-html.yml.
Expand walls.py from 17 to 22 walls, adding Serving (4), Batching (5),
Streaming (6), Tail Latency (7), and Checkpoint (19). Update paper.tex
with rewritten abstract, concrete LLaMA-3 motivating example, competitive
positioning against Calculon/ASTRA-sim/Vidur, and new overview figure.
Rebrand docs and tutorials to match.
Update display name from MLSYSIM to MLSys·im (with interpunct) in
paper title, website config, and all 18 QMD documentation pages.
Technical name (imports, file paths) remains lowercase mlsysim.
Paper subtitle updated to "First-Principles Infrastructure Modeling
for Machine Learning Systems". Preserve explicit anchor ID for
cross-referenced #extending-mlsysim heading.
- Add typed Pydantic result models (Layer A) replacing dict returns
- Add canonical Wall taxonomy registry (walls.py) as single source of truth
- Add Pipeline composer (Layer C) for solver chaining with explain()/run()
- Rename domains: Metabolism→Node, Skeleton→Data, Mind→Algorithm, World→Fleet, Meta→Analysis
- Rename MetabolismSolver→EfficiencySolver and MetabolismResult→EfficiencyResult
- Update all solver classes with walls tuple referencing canonical wall numbers
- Convert all dict access patterns to typed attribute access across codebase
Rewrite API reference pages to match domain subpackage structure.
Add solver doc pages for CompressionSolver, DataSolver,
OrchestrationSolver, and ScalingSolver. Update whitepaper,
math reference, getting-started guide, and tutorial index.
Add extending tutorial for custom solvers.
- Elevate 5-Layer Progressive Lowering mental model to architecture.qmd
- Clean up landing page copy to be a punchy one-liner
- Re-render architecture composition diagram as SVG for reliability
- Move math derivations out of tutorials and into math.qmd with citations
- Add DGX Spark to Silicon Zoo
