analytical-viz: compound tiebreaker — fewer PEs / lower HBM% when latency ties

Every place that picks a single "best" config from the Pareto set now
uses a compound sort key: (latency_ns ↑, pes_used ↑, hbm_utilization ↑).
Primary = latency; when configs tie on latency (common — cp_ring
variants, some placement variants often produce identical numbers),
prefer smaller-footprint picks.

Places updated:
  - app.py:  sidebar Apply Attn/FFN/Attn+FFN button
  - app.py:  Physical Layout tab Attn/FFN/Attn+FFN button
  - app.py:  Auto Suggest tab "Best latency" metric
  - app.py:  Auto Hardware tab "Best latency" metric (uses parallelism.pes_used
             + parallelism.hbm_utilization since JointScore wraps ConfigScore)
  - auto_hardware.py:  _best_parallelism_for_hw iteration key

No behavior change when there's a strict latency winner. When there are
ties, the picked config uses fewer PEs and lower HBM utilization.

Verified: all 24 pytest tests pass (default include_attention=True and
include_ffn=True paths unchanged).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-07-28 22:16:02 -07:00
parent 6f61657ba4
commit 2a0bc26db0
2 changed files with 22 additions and 5 deletions
@@ -245,14 +245,19 @@ def _best_parallelism_for_hw(
matches the caller's attention/FFN/full choice.
"""
best: ConfigScore | None = None
best_key: tuple | None = None
for topo in _iter_reduced_parallelism(model, s_kv, mode):
cfg = FullConfig(model=model, topo=topo, machine=machine)
s = score_config(cfg, include_attention=include_attention,
include_ffn=include_ffn)
if not (s.fits_memory and s.placement_valid):
continue
if best is None or s.total_latency_ns < best.total_latency_ns:
# Compound tiebreaker: prefer fewer PEs and lower HBM % when latency
# ties across variant knobs (cp_ring, placement, kv_shard_mode, etc.).
_k = (s.total_latency_ns, s.pes_used, s.hbm_utilization)
if best is None or _k < best_key:
best = s
best_key = _k
return best