[Benchmark] Remove the temporary bench forward dummy loader (#61676)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 13:30:18 -07:00
parent 7c3f7e5500
commit 2e8a5930f6
4 changed files with 5 additions and 29 deletions
@@ -51,9 +51,8 @@ Read `median_us` (each replay is already the max over ranks).
 ## Caveats

 - **Dummy weights lie for data-dependent kernels.** Dummy gates route every
-  token to the same experts (hence balanced routing). Dummy norm weights make
-  DSV4 indexer logits degenerate, so `topKPerRowPrefill` runs ~2.6x slow
-  until #61323 lands. Cross-check suspicious kernels with real weights.
+  token to the same experts (hence balanced routing). Cross-check suspicious
+  kernels with real weights.
 - **torch.compile models (e.g. Qwen3/3.5) look slow**: no compile here. Use
  them for correctness only; trust perf for models under `vllm/models/`.
 - `sample spread > 0.5%` warns of unstable timing. DSV4.1 DEP prefill is