Deploy audited RTX 6000D Flash-Next 128K multimodal baseline

2026-09-18 10:47:26 +08:00
commit 7e53821920
45 changed files with 1745 additions and 0 deletions
@@ -0,0 +1,7 @@
+{
+  "models/qwen4_exp/nvidia/ngram_embedding.py": "01c2cb7c691c9a8a448e57619fdb97bfe1c3230e7be3c92dd4642d3f7173a499",
+  "models/qwen4_exp/nvidia/qsa.py": "f7307663d341e3fdf5ee2ae866aaea449f1e89564938bffd66fb3211147b4f3f",
+  "models/qwen4_exp/nvidia/mtp.py": "35dc7e4b4cf124ce79a7bfc65a5f198c9edc622f1692bf6b24c91486112b7d99",
+  "model_executor/layers/quantization/modelopt.py": "e65b339d573e1650508a9ab109c29f098e0a1cc799fbe04737e96596604fff02",
+  "config/engram.py": "34043a22385a041d4e9be8857f64174c990c2ca8308b97b6a952b5ab96c20ee5"
+}