large: batch profile flipped to the runner's qualified 2048/512 (fastest measured prefill, no decode change)

scripts/frank-default-large.env

@@ -50,11 +50,12 @@ LISTEN_PORT=52625
 # while the prompt cache is enabled.
 CTX_SIZE=262144
 PARALLEL=1
-# Local override: the pinned runner uses 2048/512; production chat uses a
-# larger 4096/4096 batch (unified memory has headroom; matches the retired
-# v3 profile).
-BATCH_SIZE=4096
-UBATCH_SIZE=4096
+# Batch profile: the pinned runner's qualified sizes (2048/512). Benchmarks
+# on 2026-08-22: ubatch 512 gives the fastest prefill at every depth
+# (524/485/323 t/s at 8k/16k/64k vs 266/258/203 for ubatch 4096) with no
+# decode difference. Do not raise ubatch without re-benching prefill.
+BATCH_SIZE=2048
+UBATCH_SIZE=512
 TARGET_THREADS=16
 BATCH_THREADS=32
 CACHE_TYPE_K=f16

scripts/serve-frank-large.sh

@@ -16,9 +16,10 @@
 # differences: --host/--port come from BIND_ADDR/LISTEN_PORT (safe names;
 # the ROCm HIP runtime reads a bare HOST env var, see the 2026-08-13 TEMP
 # incident), LD_LIBRARY_PATH uses this machine's split 7.15 SDK layout,
-# the profile runs --no-mmap, batch 4096 / ubatch 4096, reasoning on with
-# deepseek format and preserve_thinking, and the target greedy argmax fast
-# path is disabled for non-greedy chat sampling.
+# the profile runs --no-mmap, reasoning on with deepseek format and
+# preserve_thinking, and the target greedy argmax fast path is disabled
+# for non-greedy chat sampling. Batch 2048 / ubatch 512 are the runner's
+# qualified sizes.
 #
 # Tunables come from frank-default-large.env in this directory unless
 # FRANK_LARGE_ENV_FILE overrides that path.
@@ -49,8 +50,8 @@ fi
 : "${LISTEN_PORT:=52625}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=4096}"
-: "${UBATCH_SIZE:=4096}"
+: "${BATCH_SIZE:=2048}"
+: "${UBATCH_SIZE:=512}"
 : "${TARGET_THREADS:=16}"
 : "${BATCH_THREADS:=32}"
 : "${CACHE_TYPE_K:=f16}"
@@ -125,10 +126,11 @@ export PROMPTFORGE_ENABLE_IU4_DECODE_M2_M5=0
 export PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=0
 
 # Pinned runner flags (qualified 262K one-slot profile, native MTP depth
-# 4, deterministic sampler). Local overrides for production chat:
+# 4, deterministic sampler; batch 2048 / ubatch 512 are the runner's
+# qualified sizes and give the fastest measured prefill). Local overrides
+# for production chat:
 #   - reasoning on + deepseek format (thinking goes to message.reasoning_content,
 #     matching the retired v3 service so the fleet's reasoning clients work)
-#   - batch 4096 / ubatch 4096 (larger than the runner's 2048/512; matches v3)
 #   - --no-mmap (local choice; benchmarks show no perf difference versus
 #     mmap, kept per operator preference)
 #   - chat_template_kwargs preserve_thinking=true (preserve thinking tokens