fix: rename sampling TEMP var to TEMPERATURE to avoid HIP runtime env collision

The ROCm HIP runtime (libamdhip64) reads the TEMP environment variable as
its JIT kernel-cache temp directory. Commit db3eb01 added TEMP=1.0 to the
env files as a sampling default; the serve scripts export it via set -a.
HIP then used the path "1.0" for its cache, failed, and segfaulted with a
NULL-refcount unref (offset 0x446153 in libamdhip64) during model tensor
upload (ggml_backend_cuda_buffer_set_tensor). This crashed frank-default-
large on every restart from Aug 13 16:22 onward; the earlier c984a3e
"fix" (KV/batch changes) was unrelated.

Rename the sampling variable TEMP -> TEMPERATURE in both env files and
serve scripts. llama-server still receives --temp from the renamed var, so
sampling defaults are unchanged. The HIP runtime no longer sees a bogus
TEMP value. Affects frank-default-large (dankclaw) and frank-default-small
(dankserver).

scripts/frank-default-large.env

@@ -36,7 +36,10 @@ UBATCH_SIZE=512
 # Sampling settings — per HauhauCS Qwen3.6-27B model card.
 # Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
 # Clients may override per-request; these are the server-side defaults.
-TEMP=1.0
+# WARNING: do not name this variable TEMP. The ROCm HIP runtime reads the
+# TEMP environment variable (JIT kernel-cache dir); TEMP=1.0 made the HIP
+# runtime SEGV (NULL unref) during model load on Aug 13 2026.
+TEMPERATURE=1.0
 TOP_K=20
 TOP_P=0.95
 MIN_P=0.0

scripts/frank-default-small.env

@@ -34,7 +34,10 @@ NO_MMAP=1
 # Sampling settings — per HauhauCS Qwen3.6-35B-A3B model card.
 # Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
 # Clients may override per-request; these are the server-side defaults.
-TEMP=1.0
+# WARNING: do not name this variable TEMP. The ROCm HIP runtime reads the
+# TEMP environment variable (JIT kernel-cache dir); TEMP=1.0 made the HIP
+# runtime SEGV (NULL unref) during model load on Aug 13 2026.
+TEMPERATURE=1.0
 TOP_K=20
 TOP_P=0.95
 MIN_P=0.0

scripts/serve-llama-frank-large.sh

@@ -37,7 +37,7 @@ fi
 : "${CACHE_TYPE_V:=q8_0}"
 : "${BATCH_SIZE:=2048}"
 : "${UBATCH_SIZE:=512}"
-: "${TEMP:=1.0}"
+: "${TEMPERATURE:=1.0}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.95}"
 : "${MIN_P:=0.0}"
@@ -72,7 +72,7 @@ exec "$LLAMA_SERVER" \
     --parallel "$PARALLEL" \
     --batch-size "$BATCH_SIZE" \
     --ubatch-size "$UBATCH_SIZE" \
-    --temp "$TEMP" \
+    --temp "$TEMPERATURE" \
     --top-k "$TOP_K" \
     --top-p "$TOP_P" \
     --min-p "$MIN_P" \

scripts/serve-llama-frank-small.sh

@@ -38,7 +38,7 @@ fi
 : "${UBATCH_SIZE:=512}"
 : "${CTX_CHECKPOINTS:=0}"
 : "${NO_MMAP:=0}"
-: "${TEMP:=1.0}"
+: "${TEMPERATURE:=1.0}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.95}"
 : "${MIN_P:=0.0}"
@@ -74,7 +74,7 @@ exec "$LLAMA_SERVER" \
     --ubatch-size "$UBATCH_SIZE" \
     --ctx-checkpoints "$CTX_CHECKPOINTS" \
     $([ "$NO_MMAP" = "1" ] && printf -- "--no-mmap") \
-    --temp "$TEMP" \
+    --temp "$TEMPERATURE" \
     --top-k "$TOP_K" \
     --top-p "$TOP_P" \
     --min-p "$MIN_P" \