feat: Variet Engine v1.0 + 5-model tuning complete

Phase 01 (LLM Tuning):
- Gemma4 26B: 74.65 t/s (fast)
- Qwen 35B: 61.62 t/s (balanced)
- Gemma4 31B: 16.0 t/s (deep-coder)
- Qwen 27B: 16.7 t/s (deep-logic)
- Qwen 122B: 8.95 t/s (ultra, GPU 1 only)

Phase 02 (API Engine):
- FastAPI reverse proxy on port 8000
- /engine/switch hot-swap with 503 protection
- config/engine_models.json as single source of truth
- Replaced 4 individual .bat files with unified engine

File cleanup:
- scripts/ 85 files -> 9 + _archive/
- Root .bat files -> _archive/
This commit is contained in:
Variet-Worker
2026-04-07 18:08:58 +09:00
parent 7c7a899fd5
commit c111b3a9b0
414 changed files with 3402 additions and 68598 deletions

7
_archive/models_list.txt Normal file
View File

@@ -0,0 +1,7 @@
C:\Users\Variet-Worker\Desktop\variet-llm\models\gemma-4-26B-A4B-it-MXFP4_MOE.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\gemma-4-26B-A4B-it-Q4_K_M.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\Qwen3.5-35B-A3B-MXFP4_MOE.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\Qwen3.5-35B-A3B-Q4_K_M.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-00002-of-00003.gguf
C:\Users\Variet-Worker\Desktop\variet-llm\models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-00003-of-00003.gguf