|
|
@@ -114,6 +114,13 @@ args = [
|
|
|
# must stay ≥88; r12-era this cluster dropped it to 74 — r17 may carry
|
|
|
# the fix through — one boot decides).
|
|
|
"--block-size", "256",
|
|
|
+ # FINAL BISECT (2026-09-03, hardmode 176pt, r17 img):
|
|
|
+ # knobs-only 87: d0 c1 24.1, d8192 23.8
|
|
|
+ # +moe b12x 88: d0 c1 23.5, d8192 26.6 <- SHIP (2 pts d8192)
|
|
|
+ # +linear b12x 44: W4A4 linear kernel destroys numerics (param-precision 0%)
|
|
|
+ # +align 88: but d0 c1 18.6 (-5) — perf-negative, dropped
|
|
|
+ # (all three together = 44-74; the lab needs its private packed package)
|
|
|
+ "--moe-backend", "b12x",
|
|
|
"--max-model-len", "524288",
|
|
|
"--max-num-seqs", "16",
|
|
|
"--max-num-batched-tokens", "4096",
|
|
|
@@ -134,7 +141,7 @@ args = [
|
|
|
# SPECULATIVE config, not the global flag (eagle/utils.py:
|
|
|
# _make_eagle_draft_vllm_config) — B12X here mirrors the main model's.
|
|
|
"--speculative-config", """
|
|
|
-'{"method":"mtp","num_speculative_tokens":3,"moe_backend":"b12x","attention_backend":"B12X"}'""",
|
|
|
+'{"method":"mtp","num_speculative_tokens":3,"attention_backend":"B12X"}'""",
|
|
|
"--language-model-only",
|
|
|
# MTP + CUDA graphs degrades OUTPUT QUALITY on the glm53 day-0 dev build
|
|
|
# (forum #381350/#44, CONFIRMED by A/B bench 2026-08-28: same seed/flags,
|
