frank-default-small: prefill-max ncmoe 35 / ubatch 3072

Prefill is the priority for this workload. Switch from decode-max
(ncmoe 32 / ubatch 1024) to prefill-max:
- n-cpu-moe 35, ubatch 3072: prefill ~1458 t/s (top tier), gen ~45.4 t/s,
  ~1.2 GiB headroom at the 800k pool.
- Gen is independent of ubatch; ub 3072 reaches best prefill with no
  decode cost. Docs synced (benchmark Chosen State, deployment, specs).

scripts/frank-default-small.env

@@ -8,17 +8,17 @@ PORT=7770
 # (Increased from 3×200k to add a 4th parallel stream.)
 CTX_SIZE=800000
 PARALLEL=4
-# Spec: ngram-mod. n_min=48, n_max=64, n_match=24 (defaults). 8 expert
-# layers back on GPU; 32 on CPU. Batch 8192 / ubatch 1024.
+# Spec: ngram-mod. n_min=48, n_max=64, n_match=24 (defaults). 5 expert
+# layers back on GPU; 35 on CPU. Batch 8192 / ubatch 3072.
 SPEC_TYPE=ngram-mod
 NGRAM_MOD_N_MIN=48
 NGRAM_MOD_N_MAX=64
 NGRAM_MOD_N_MATCH=24
-# Expert offload: 32 of 40 layers keep MoE weights on CPU; remaining
-# 8 layers have their expert weights resident on GPU for faster routing.
-# Benchmark-chosen (see frank-default-small-benchmark.md): max decode at
-# the headroom that stays above the historical OOM boundary.
-N_CPU_MOE=32
+# Expert offload: 35 of 40 layers keep MoE weights on CPU; remaining
+# 5 layers have their expert weights resident on GPU for faster routing.
+# Benchmark-chosen (see frank-default-small-benchmark.md): prefill-max.
+# gen ~45.4 t/s, pp ~1458 t/s, ~1.2 GiB headroom.
+N_CPU_MOE=35
 N_GPU_LAYERS=all
 # KV cache on GPU, K quantized to q8_0, V stays f16 (user-locked decision).
 CACHE_TYPE_K=q8_0
@@ -27,10 +27,10 @@ CACHE_TYPE_V=f16
 # larger batch/ubatch (leaves headroom for ctx-checkpoints operation).
 CTX_CHECKPOINTS=4
 # Larger batches / ubatch for big prefill workloads.
-# ubatch 1024 (benchmark-chosen): decode is flat vs ubatch; 1024 frees
-# compute-graph VRAM to afford ncmoe 32 while keeping prefill ~766 t/s.
+# ubatch 3072 (benchmark-chosen): prefill is the priority; this is the top
+# prefill tier (~1458 t/s) with ~1.2 GiB headroom. Decode is independent.
 BATCH_SIZE=8192
-UBATCH_SIZE=1024
+UBATCH_SIZE=3072
 # Load the model into RAM rather than lazy-mapping it. The MoE experts live on
 # CPU, so eager RAM load avoids page faults during decode (uses ~31GB RAM).
 NO_MMAP=1

scripts/serve-llama-frank-small.sh

@@ -32,10 +32,10 @@ fi
 : "${NGRAM_MOD_N_MATCH:=24}"
 : "${CACHE_TYPE_K:=q8_0}"
 : "${CACHE_TYPE_V:=f16}"
-: "${N_CPU_MOE:=32}"     # 32 of 40 layers: MoE expert weights stay on CPU; 8 on GPU
+: "${N_CPU_MOE:=35}"     # 35 of 40 layers: MoE expert weights stay on CPU; 5 on GPU
 : "${N_GPU_LAYERS:=all}" # every non-expert tensor goes to GPU
 : "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=1024}"
+: "${UBATCH_SIZE:=3072}"
 : "${CTX_CHECKPOINTS:=0}"
 : "${NO_MMAP:=0}"
 : "${TEMPERATURE:=1.0}"