ljsysfurry commited on
Commit
6d70c2b
·
verified ·
1 Parent(s): ccb11fc

Upload mla_absorbed_cache_report.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. mla_absorbed_cache_report.md +1 -1
mla_absorbed_cache_report.md CHANGED
@@ -196,4 +196,4 @@ k_pe 的 INT8 误差仅 0.005,比 latent 还稳——因为它只编码位置
196
  - `l40s_quant.py` — per-channel/per-tensor 量化对比
197
  - `l40s_opt3.py` — 深度优化(k_pe 量化/混合精度/INT4)
198
 
199
- *Cloud LTE Studio · 2026-08-08 · MIT License*
 
196
  - `l40s_quant.py` — per-channel/per-tensor 量化对比
197
  - `l40s_opt3.py` — 深度优化(k_pe 量化/混合精度/INT4)
198
 
199
+ *Cloud LTE Studio · 2026-08-08 · GPL-3.0 License*