Commit Graph

11 Commits

Author SHA1 Message Date
Vijay Janapa Reddi
46fdae75b0 docs: auto-format print statements to tables across tutorials 2026-03-13 09:05:17 -04:00
Vijay Janapa Reddi
6f973091e1 docs(mlsysim): refactor tutorial 01 to use mlsysim.show utilities 2026-03-13 08:50:36 -04:00
Vijay Janapa Reddi
2bbe3e1a69 docs(mlsysim): redesign website, add 12 tutorials, and CLI entry points
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.
2026-03-12 16:04:51 -04:00
Vijay Janapa Reddi
5c52507f27 feat(mlsysim): add prompt caching to ServingSolver and release-readiness fixes
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.
2026-03-12 16:04:51 -04:00
Vijay Janapa Reddi
1b32571af7 docs(mlsysim): harmonize website with paper and add 5 tutorials
Website-paper consistency:
- Rename Operations to Ops across architecture, glossary, solver-guide
- Fix Mermaid diagram arrows for progressive lowering
- Add extensibility section to architecture page
- Add workload types table to getting-started and zoo/models
- Add Binding Constraint and Systems Wall to glossary
- Expand sidebar to list all 10 tutorials

New tutorials covering all 6 paper domains:
- design_space.qmd: bottleneck regime map (Node domain)
- data_pipeline.qmd: CPU bottleneck analysis (Data domain)
- cot_economics.qmd: inference cost scaling (Algorithm domain)
- sensitivity.qmd: binding constraint audit (Analysis domain)
- architecture_comparison.qmd: GPU vs Cerebras (Node domain)

Persona page updates:
- for-students: expanded learning path to 8 tutorials
- for-instructors: expanded course integration to 7 weeks
- for-engineers: added sensitivity and architecture links
2026-03-12 16:04:50 -04:00
Vijay Janapa Reddi
d594b4abd0 docs(mlsysim): expand to 22-wall taxonomy with paper rewrite and overview figure
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.
2026-03-12 16:04:50 -04:00
Vijay Janapa Reddi
8db12f0ee4 refactor(mlsysim): rebrand MLSYSIM to MLSys·im across paper and website
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.
2026-03-12 16:04:50 -04:00
Vijay Janapa Reddi
289e018223 refactor(mlsysim): typed results, wall taxonomy, and engineering naming
- 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
2026-03-12 16:04:50 -04:00
Vijay Janapa Reddi
7b145803c3 docs(mlsysim): update API docs, tutorials, and whitepaper for new architecture
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.
2026-03-12 16:04:50 -04:00
Vijay Janapa Reddi
aed43c5b81 docs: clean up landing page and centralize math foundations
- 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
2026-03-07 18:37:06 -05:00
Vijay Janapa Reddi
a78f1bd8b0 feat(mlsysim): add documentation site, typed registries, and 6-solver core
Complete MLSYSIM v0.1.0 implementation with:

- Documentation website (Quarto): landing page with animated hero
  and capability carousel, 4 tutorials (hello world, LLM serving,
  distributed training, sustainability), hardware/model/fleet/infra
  catalogs, solver guide, whitepaper, math foundations, glossary,
  and full quartodoc API reference
- Typed registry system: Hardware (18 devices across 5 tiers),
  Models (15 workloads), Systems (fleets, clusters, fabrics),
  Infrastructure (grid profiles, rack configs, datacenters)
- Core types: Pint-backed Quantity, Metadata provenance tracking,
  custom exception hierarchy (OOMError, SLAViolation)
- SimulationConfig with YAML/JSON loading and pre-validation
- Scenario system tying workloads to systems with SLA constraints
- Multi-level evaluation scorecard (feasibility, performance, macro)
- Examples, tests, and Jetson Orin NX spec fix (100 → 25 TFLOP/s)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 15:59:51 -05:00