frank-default-large: re-enable --flash-attn on via QSA F32-mask patch

fa on aborted graph build: build_attn_qsa called ggml_fill on the
F16-converted kq mask (GGML_ASSERT F32 at ggml.c:5371). Patch mirrors the
MLA sparse path in llm_graph_context::build_attn (F32 base mask for the
top-k surgery, F16 cast only at the attention call, gated on
cparams.flash_attn). Vendored at scripts/patches/qwen4exp-qsa-f32-mask.patch
(sha256 f2f4a486...); the build-qwen38 binary on Dankclaw is rebuilt with
it and validated live at CTX_SIZE=32768 (health 200, real completion).

scripts/frank-default-large.env

@@ -10,12 +10,16 @@
 #
 # Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
 # 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
-# KNOWN CONSTRAINTS on the charlie12345/ROCmFPX build-qwen38 runtime.
-# 1. FA must stay OFF. --flash-attn on aborts graph build: the QSA
-#    indexer path calls ggml_fill on the F16-cast kq mask (ggml_fill
-#    asserts GGML_TYPE_F32 at ggml.c:5371). The v2 main loads and serves
-#    fine with --flash-attn off (verified live: model loaded, health 200,
-#    real completion).
+# 1. Flash attention is ON. fa on used to abort graph build: the QSA
+#    indexer path called ggml_fill on the F16-cast kq mask (ggml_fill
+#    asserts GGML_TYPE_F32 at ggml.c:5371). Fixed in the fork source by
+#    the QSA F32-mask patch (scripts/patches/qwen4exp-qsa-f32-mask.patch,
+#    sha256 f2f4a486e21cfad80bfa42683281d18e1cba22fa43c5e0e2aa0cfdbe141e925f)
+#    and the rebuilt binary at LLAMA_BIN already carries the fix. A clean
+#    rebuild must re-apply: git apply scripts/patches/qwen4exp-qsa-f32-mask.patch
+#    inside /home/dank/GitPackages/ROCmFPX before make. Verified live:
+#    --flash-attn on + v2 main at CTX_SIZE=32768 loads, health 200, real
+#    completion.
 # 2. The MTP draft head does NOT load on this binary. The qwen4exp loader
 #    requires blk.0.hc_attn_norm.weight per layer; the agentionai FAST
 #    head carries only blk.48 (verified 3x: EasiiX Q8_0 + FAST against
@@ -54,7 +58,7 @@ ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 
-# Serving: 131072-token context on ONE slot (parallel 1), batch 4096 /
+# Serving: 32768-token context on ONE slot (parallel 1), batch 4096 /
 # ubatch 4096, 16+16 threads, f16 KV, 16 context checkpoints, 8 GiB
 # prompt cache. --fit off: auto-fit segfaults on this model's
 # hyper-connection/indexer config; -ngl 999 puts every layer on the
@@ -81,7 +85,7 @@ SLOT_SAVE_PATH=/home/dank/serverAppConfigs/scripts/slot-state
 SPLIT_MODE=none
 FIT=off
 NGL=999
-FLASH_ATTN=off
+FLASH_ATTN=on
 
 # Sampling (card instruct table, non-thinking).
 TEMPERATURE=0.7

scripts/patches/qwen4exp-qsa-f32-mask.patch

@@ -0,0 +1,31 @@
+--- a/src/models/qwen4exp.cpp
++++ b/src/models/qwen4exp.cpp
+@@ -560,9 +565,13 @@ ggml_tensor * llama_model_qwen4exp::graph::build_attn_qsa(
+         ggml_build_forward_expand(gf, mctx_cur->cpy_k(ctx0, k_cur, k_idxs, il));
+         ggml_build_forward_expand(gf, mctx_cur->cpy_v(ctx0, v_cur, v_idxs, il));
+     }
+ 
+-    ggml_tensor * kq_mask = inp->get_kq_mask();
++    // get_kq_mask() returns the F16-converted mask when flash attention is
++    // on, but ggml_fill/set_rows require F32. Mirror the MLA sparse path
++    // (llm_graph_context::build_attn): run the top-k mask surgery on the F32
++    // base mask and cast to the attention type only at the end.
++    ggml_tensor * kq_mask = inp->self_kq_mask;
+ 
+     // prepare new kq mask - starts filled with -INFINITY
+     ggml_tensor * kq_mask_all = ggml_fill(ctx0, kq_mask, -INFINITY);
+ 
+@@ -592,9 +601,12 @@ ggml_tensor * llama_model_qwen4exp::graph::build_attn_qsa(
+     ggml_tensor * q = q_cur;
+     ggml_tensor * k = mctx_cur->get_k(ctx0, il);
+     ggml_tensor * v = mctx_cur->get_v(ctx0, il);
+ 
+-    ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, kq_scale, il);
++    // flash attention consumes an F16 mask; softmax consumes F32 as-is
++    ggml_tensor * kq_mask_attn = inp->cparams.flash_attn ? ggml_cast(ctx0, kq_mask_top_k, GGML_TYPE_F16) : kq_mask_top_k;
++
++    ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_attn, nullptr, nullptr, kq_scale, il);
+     cb(cur, "kqv_out", il);
+ 
+     return cur;
+ }

scripts/serve-frank-large.sh

@@ -59,7 +59,7 @@ fi
 : "${SPLIT_MODE:=none}"
 : "${FIT:=off}"
 : "${NGL:=999}"
-: "${FLASH_ATTN:=off}"
+: "${FLASH_ATTN:=on}"
 : "${TEMPERATURE:=0.7}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.8}"