diff --git a/docs/design/skip_softmax_sage_trtllm_gen.md b/docs/design/skip_softmax_sage_trtllm_gen.md index 747d4e67b..e1ec3073e 100644 --- a/docs/design/skip_softmax_sage_trtllm_gen.md +++ b/docs/design/skip_softmax_sage_trtllm_gen.md @@ -1,10 +1,5 @@ # SAGE + Skip-Softmax — API Design & Test Plan -Backend: **trtllm-gen** (FlashInfer). Primary metric: **LPIPS ↓** vs BF16 dense. Speedup vs BF16 dense. -Order: **(1) SAGE → (2) Skip → (3) SAGE + Skip → (4) cross-backend.** - ---- - # Part 1 — API Design *How the user uses the trtllm-gen backend.*