anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

docs: drop Notes section

Browse Source
This commit is contained in:
lishunyang12 committed 2026-07-15 10:09:07 +00:00
1 parent 20b8a77605
commit c695836d81
1 file changed
-6
Download Patch File Download Diff File Expand all files Collapse all files
docs/design/skip_softmax_sage_trtllm_gen.md
-6
View File
@@ -169,9 +169,3 @@ Fix one model + shape + seed, swap only the attention backend. Speedup vs SDPA (
| **trtllm-gen** | FP8-SAGE | | | |
| **trtllm-gen** | FP8-SAGE+Skip | | | |
---
### Notes
- SAGE = no calibration; Skip = per-model calibration.
- LPIPS measured vs **BF16 dense**; perf on the **target Blackwell SKU under real concurrency**.