[Public release 26/04] Introducing Mega MoE, FP4 Indexer and other features/fixes (#304)

* Merge with private repo * Update README * Update README * Update README * Add PyTorch requirements * Fix sync scopes for MQA logits (#256) * Update README
2026-04-17 09:45:14 +08:00
parent d30fc36c8f
commit 7f2a703ed5
109 changed files with 12101 additions and 3219 deletions
@@ -10,7 +10,11 @@ except ImportError:
    pass

 # Valid for all CUDA versions
-from .._C import get_mk_alignment_for_contiguous_layout
+from .._C import (
+    set_mk_alignment_for_contiguous_layout,
+    get_mk_alignment_for_contiguous_layout,
+    get_theoretical_mk_alignment_for_contiguous_layout,
+)

 # Some alias
 get_m_alignment_for_contiguous_layout = get_mk_alignment_for_contiguous_layout