c111b3a9b0
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/
68 lines
1.5 KiB
JSON
68 lines
1.5 KiB
JSON
[
|
|
{
|
|
"name": "Qwen 27B - 256K (q4_0)",
|
|
"status": "Success",
|
|
"vram": [
|
|
"0, 10853 MiB, 12288 MiB",
|
|
"1, 10951 MiB, 12288 MiB"
|
|
],
|
|
"tests": {
|
|
"code": {
|
|
"time": 17.89,
|
|
"tokens": 300,
|
|
"tps": 16.77,
|
|
"res": "..."
|
|
},
|
|
"logical": {
|
|
"time": 17.96,
|
|
"tokens": 300,
|
|
"tps": 16.71,
|
|
"res": "..."
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "Gemma 31B - 32K (q4_0)",
|
|
"status": "Success",
|
|
"vram": [
|
|
"0, 9834 MiB, 12288 MiB",
|
|
"1, 9963 MiB, 12288 MiB"
|
|
],
|
|
"tests": {
|
|
"code": {
|
|
"time": 18.75,
|
|
"tokens": 300,
|
|
"tps": 16.0,
|
|
"res": "```python\nfrom typing import List, Any\n\ndef merge_sorted_lists(list1: List[Any], list2: List[Any]) -> List[Any]:\n \"\"\"\n Merges two sorted lists i..."
|
|
},
|
|
"logical": {
|
|
"time": 18.82,
|
|
"tokens": 300,
|
|
"tps": 15.94,
|
|
"res": "..."
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "Gemma 31B - 64K (q4_0)",
|
|
"status": "Success",
|
|
"vram": [
|
|
"0, 10346 MiB, 12288 MiB",
|
|
"1, 10387 MiB, 12288 MiB"
|
|
],
|
|
"tests": {
|
|
"code": {
|
|
"time": 18.75,
|
|
"tokens": 300,
|
|
"tps": 16.0,
|
|
"res": "```python\nfrom typing import List, Any\n\ndef merge_sorted_lists(list1: List[Any], list2: List[Any]) -> List[Any]:\n \"\"\"\n Merges two sorted lists i..."
|
|
},
|
|
"logical": {
|
|
"time": 18.83,
|
|
"tokens": 300,
|
|
"tps": 15.93,
|
|
"res": "..."
|
|
}
|
|
}
|
|
}
|
|
] |