 woolcoxm
|
e71d4fbe29
|
windows-dev: CUDA build script, expert budget + grouped quant research
- build_cuda.bat: one-shot nvcc DLL compilation for sm_120 (RTX 5070 Ti)
- issue_budget.md: EXPERT_BUDGET research (cap distinct experts/layer, 2x tok/s)
- issue_grouped_quant.md: root cause of int4 incoherence (per-row vs group-128 scales)
- glm_fp8_emit.py: FP8 e4m3 test weight generator for converter validation
|
2026-07-15 02:32:12 -04:00 |
|