Fix #679: Generate GENOME.md for turboquant

Browse Source

- Created comprehensive GENOME.md with full codebase analysis
- Added architecture diagram (Mermaid)
- Documented entry points and data flow
- Identified key abstractions
- Mapped API surface (C, Metal, CLI)
- Identified test coverage gaps
- Documented security considerations
- Added basic test suite (9 tests passing)

Key findings:
- 73.4% KV memory savings (turbo4 vs f16)
- ~1% prompt overhead, ~11% generation overhead
- PolarQuant + QJL = 3.5 bits/channel
- Metal shaders exist on feature branch
- CPU reference incompatible with Metal dequant
- QJL infrastructure present but disabled

Test coverage gaps:
- No unit tests for encode/decode
- No integration tests
- No perplexity runner (corpus exists)
- No Metal vs CPU parity tests

Security considerations:
- Buffer overflow risk in bit packing
- No constant-time implementation
- No safety wrapper for C/C++ code

...

This commit is contained in:

Alexander Whitestone

2026-04-14 19:03:21 -04:00

parent 7a7ce0e652

commit f60604ddcc

3 changed files with 464 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

tests/__pycache__/test_turboquant.cpython-312-pytest-9.0.2.pyc Normal file

Binary file not shown.