Skip to content

armgit / Edge0

Public Imported from GitHub
0

Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

Python

README: drop numerical-guard bullet from public feature list

linyubupa5f70676cdf41
diff --git a/README.md b/README.md
index 7f3e699..d9ca5de 100644
--- a/README.md
+++ b/README.md
@@ -76,10 +76,7 @@ are co-located with each checkpoint and load automatically, so
with model size, routed width (K), and memory pressure;
- **Parallel LoRA**: adapters are applied as a side path at forward
time instead of being merged — the base stays a read-only mmap and
- multiple adapter sets share one base;
-- **Numerical guard**: per-layer hidden clipping (`LING_HIDDEN_CLIP`,
- default 1000) breaks the fp16 overflow → all-NaN logits → token-0
- death-spiral collapse chain.
+ multiple adapter sets share one base.
## Quick start
diff --git a/README_zh.md b/README_zh.md
index f2502a8..8216f54 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -58,9 +58,7 @@
**存储越慢,收益越大**:该机制消除的正是专家工作集超出常驻容量时占
主导的冷读等待,因此收益随模型规模、路由宽度(K)与内存压力增大;
- **并行 LoRA**:适配器不合并进基模,前向时旁路叠加,
- 基模保持只读 mmap、多套适配器共享同一份基模;
-- **数值防护**:per-layer hidden clip(`LING_HIDDEN_CLIP`,默认 1000)
- 阻断 fp16 溢出 → 全 NaN logits → token-0 死循环的塌缩链。
+ 基模保持只读 mmap、多套适配器共享同一份基模。
## 快速开始