integrate Flash Attention 3. +9% tok_per_sec for d12 with ctx even as low as 2048 out of the box nice. also, ready to tune windows huge

2026-01-30 04:22:02 +00:00 · 2026-01-11 20:33:19 +00:00
parent 201d705957
commit 2ff7d51252
6 changed files with 177 additions and 143 deletions
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -8,6 +8,7 @@ dependencies = [
    "datasets>=4.0.0",
    "fastapi>=0.117.1",
    "ipykernel>=7.1.0",
+    "kernels>=0.11.7",
    "matplotlib>=3.10.8",
    "psutil>=7.1.0",
    "python-dotenv>=1.2.1",