basal-2.0 card (private)

README.md

@@ -143,7 +143,7 @@ basal-1.5 is basal-1.5-mini, the previous release. **Werdykt** rows are the publ
 - **Training.** Trained further from earlier basal checkpoints. The mini is a full fine-tune distilled from basal-2.0-max.
 - **Calibration.** Temperatures per question type and option-count bucket, fitted on question families the model was
   not trained on.
-- **Engine v2.0.0.** Compact batching (+19% decisions/s at 16 clients, +17% at 32, +8% at one client) and a prompt-template cache (+20% at 8 clients) (one H100, bf16, each change left out in turn). Engine v2.0.0 schedules long requests (over 2,048 tokens) behind short ones: in a mixed load at 32 clients short requests answer in 0.81 s instead of 1.38 s (p50), and long requests take about 7% longer (p50 1.96 s instead of 1.83 s); `--scheduler off` serves in arrival order.
+- **Engine v2.0.0.** Compact batching (+19% decisions/s at 16 clients, +17% at 32, +8% at one client) and a prompt-template cache (+20% at 8 clients) (one H100, bf16, each change left out in turn). They need FlashAttention 3 (Hopper): the Werdykt rows on this card ran with FlashAttention 3; the release check, the port checks, the FP8 speed and the calibration ran with FlashAttention 2, without them. Engine v2.0.0 schedules long requests (over 2,048 tokens) behind short ones: in a mixed load at 32 clients short requests answer in 0.81 s instead of 1.38 s (p50), and long requests take about 7% longer (p50 1.96 s instead of 1.83 s); `--scheduler off` serves in arrival order.
 
 ## Ports
 
@@ -182,7 +182,7 @@ One decision = one question, one option order. Hardware is named on every number
   basal-1.5 20.5 decisions/s at 16 clients, c1 p50 14 ms (p95 346 ms) in basal-serve's default mode, as on the public board.
   Separate pods of the same GPU type.
 - FP8 package: 103.5 dec/s c16, c1 p50 14 ms (H100); one NVIDIA H100 80GB (cluster node), one option order.
-- Engine items on for this model: bf16 and FP8: compact rows, template prefix, scheduler, truncation on; flex, readout-only off.
+- Measured setup: the Werdykt rows (accuracy and the speed pass) ran on the Werdykt pods with FlashAttention 3 installed, which the engine needs for compact rows and the template prefix (both engine defaults); the release check, the port checks, the FP8 speed and the calibration fits ran with FlashAttention 2, so compact rows and the template prefix were off there. FP8 keeps FlashAttention 2 unless `--attn fa3`.
 - Accuracy rows use `--deterministic`; default minus `--deterministic` accuracy on dev v2: bf16 +0.0000, FP8 +0.0016 (run 1; 32 requests in flight); `--deterministic` itself: bf16 200/200 identical at 16 clients, FP8 200/200 identical at 16 clients.
 
 **basal-1.5's other configuration.** basal-1.5 also shipped FP8 checkpoints served by vLLM. On one RunPod H100 (median of