Add MTP_N_PARALLEL to entrypoint.sh, bump submodule pointers

entrypoint.sh now honors MTP_N_PARALLEL (default 1, unchanged) for
-np instead of hardcoding 1, so open-webui's docker-compose.mtp.yaml
can request multiple llama-server slots.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

mtp-relaxed-decoding/entrypoint.sh

@@ -9,6 +9,7 @@ set -euo pipefail
 : "${MTP_CTX_SIZE:=8192}"
 : "${MTP_BATCH_SIZE:=512}"
 : "${MTP_TEMP:=0.6}"
+: "${MTP_N_PARALLEL:=1}"
 
 args=(
   --model "$MTP_TARGET_GGUF"
@@ -18,7 +19,7 @@ args=(
   --spec-draft-relaxed-top-n "$MTP_RELAXED_TOP_N" --spec-draft-backend-sampling
   --spec-draft-model "$MTP_DRAFT_GGUF" -ngl 999 --spec-draft-ngl 999
   --flash-attn auto -c "$MTP_CTX_SIZE" -b "$MTP_BATCH_SIZE" -ub "$MTP_BATCH_SIZE"
-  --context-shift --keep 4 -np 1 --temp "$MTP_TEMP"
+  --context-shift --keep 4 -np "$MTP_N_PARALLEL" --temp "$MTP_TEMP"
 )
 
 if [[ -n "${MTP_AUTH_TOKEN:-}" ]]; then