Snider
|
7915f7ad3c
|
docs: graduate TODO/FINDINGS into production documentation
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-20 15:03:17 +00:00 |
|
Claude
|
4b6cffb9c4
|
docs: Phase 4 performance implementation plan
5 tasks: go-inference ParallelSlots, wire --parallel, benchmark
suite, flash attention comparison, documentation.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 23:11:30 +00:00 |
|
Claude
|
31bf0e8850
|
docs: Phase 4 performance design
Benchmark suite (testing.B), parallel slots via go-inference,
flash attention manual comparison.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 23:09:56 +00:00 |
|
Claude
|
f8b091f511
|
docs: Phase 3 model support implementation plan
4 tasks: GGUF metadata parser, model discovery, LoadModel
enrichment, integration tests + documentation.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 22:12:31 +00:00 |
|
Claude
|
2454761e34
|
docs: Phase 3 model support design — approved
GGUF metadata parser, model discovery, LoadModel enrichment,
chat template verification.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 22:04:18 +00:00 |
|
Claude
|
d963cbf787
|
docs: Phase 2 robustness implementation plan
5 tasks: crash detection, port retry, VRAM monitoring,
graceful shutdown test, concurrent requests test.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 21:31:24 +00:00 |
|
Claude
|
2f743c5772
|
docs: Phase 2 robustness design — approved
Covers: graceful shutdown verification, port conflict retry,
server crash detection, VRAM monitoring via sysfs, concurrent
request testing.
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 21:26:41 +00:00 |
|
Claude
|
9dda860df4
|
docs: incorporate Charon review — safer serverEnv() filtering
Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-19 20:47:16 +00:00 |
|
Claude
|
acf79e3351
|
docs: Phase 1 implementation plan
Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-19 20:38:11 +00:00 |
|
Claude
|
34407a69ca
|
docs: Phase 1 core implementation design
Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-19 20:32:22 +00:00 |
|