frank-small: Swift-1.5-27B Uncensored RCO-IQ3_XXS with MTP back on (two 131072 slots, ubatch 512, q8_0 KV, publisher's BF16 mmproj)

scripts/serve-frank-small.sh

@@ -1,24 +1,24 @@
 #!/usr/bin/env bash
-# Serve ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF (IQ3_S **-mtp**) as
-# frank-small on Dankclaw's RTX 3090 via llama.cpp (master build, CUDA
-# sm_86).
+# Serve ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF
+# (RCO-IQ3_XXS, **MTP head in the file**) as frank-small on Dankclaw's
+# RTX 3090 via llama.cpp (master build, CUDA sm_86).
 #
-# 2026-10-06 (Frank): the 128k cap keeps the per-conversation window but
-# the pool doubles to TWO 131,072 conversations (262144 / 2), speculative
-# decoding is OFF (no draft-mtp; ngram skipped — on a qwen35 hybrid it
-# disables recurrent-state rollback), and ubatch drops to 512. Frank
-# accepted the tight fit explicitly (the 2-3 GiB floor is knowingly
-# violated; frank-small.env carries the arithmetic). The q8_0 KV contract
-# (FP8 class) is unchanged; the per-tensor flags stay explicit either way.
+# 2026-10-06 (Frank): TWO 131,072 conversations (262144 / 2) at the 128k
+# cap, ubatch 512, and MTP BACK ON (draft-mtp, depth 3 — the payload is
+# 1.56 GiB lighter than the IQ3_S-mtp it replaced, which is what funds
+# the draft ctx plus the second slot; ngram stays skipped — on a qwen35
+# hybrid it disables recurrent-state rollback). The q8_0 KV contract
+# (FP8 class) is unchanged; the per-tensor flags stay explicit either
+# way.
 #
 # Architecture: qwen35 hybrid — 64 real layers, 16 full-attention + 48
 # Gated DeltaNet (full_attention_interval 4), native 262144 window, plus
 # the blk.64 MTP head (nextn_predict_layers=1). KV lives only in the 16
 # attention layers (34 KiB/token at q8_0); the DeltaNet state is per-slot
-# fixed size. Vision comes from the projector file (the GGUF carries no
-# vision tensors; unsloth's mmproj built from the shared Qwen3.8-27B base —
-# proven byte-identical to Swift's own tower, see download-frank-small.sh),
-# so --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is the
+# fixed size.
+# Vision comes from the projector file (the GGUF carries no vision
+# tensors; the publisher SHIPS mmproj-BF16.gguf in the same repo), so
+# --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is the
 # documented text-only opt-out.
 #
 # Sampling: llama.cpp takes it per request (the fleet harness sends its
@@ -38,7 +38,7 @@ fi
 
 # --- defaults (used when the env file does not set them) -------------------
 : "${LLAMA_BIN:=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
-: "${MODEL_FILE:=/home/dank/models/Swift15-IQ3S/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf}"
+: "${MODEL_FILE:=/home/dank/models/Swift15-UncIQ3XXS/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf}"
 : "${ALIAS:=frank-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
@@ -61,15 +61,16 @@ fi
 # visible in the argv.
 : "${CACHE_TYPE_K:=q8_0}"
 : "${CACHE_TYPE_V:=q8_0}"
-# Speculative decoding is OFF by default (Frank, 2026-10-06): SPEC_TYPE
-# none strips BOTH speculative flags (flags move as a set). Setting a
-# drafter here re-enables the pair — draft-mtp needs the head that is IN
-# the -mtp GGUF.
-: "${SPEC_TYPE:=none}"
+# Speculative decoding is ON by default (Frank, 2026-10-06 evening):
+# draft-mtp against the head that is IN the file. SPEC_TYPE none strips
+# BOTH speculative flags (flags move as a set) — a no-spec baseline must
+# not carry half a spec pair.
+: "${SPEC_TYPE:=draft-mtp}"
+: "${SPEC_DRAFT_N_MAX:=3}"
 : "${NGL:=99}"
 # Vision projector. No colon on purpose: an explicitly empty value means
 # "text-only, on purpose" and must NOT be replaced by the default path.
-: "${MMPROJ_FILE=/home/dank/models/Swift15-IQ3S/mmproj-Qwen3.8-27B-F16.gguf}"
+: "${MMPROJ_FILE=/home/dank/models/Swift15-UncIQ3XXS/mmproj-BF16.gguf}"
 
 # Fail loudly rather than half-loading: a missing file is a download that
 # has not finished, and Restart=always would turn it into a crash loop that