From 7a149bfb48bf5ad2351b09305d13c27c38c583c0 Mon Sep 17 00:00:00 2001
From: Story Crater Bot <19826264+Riotpiaole@users.noreply.github.com>
Date: Fri, 21 Aug 2026 13:21:41 -0700
Subject: [PATCH] fix: use pipeline parallelism instead of TP for
 reasoning-predictor (bnb prequant blocks TP)

---
 k8s/apps/llm-serving/reasoning.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/k8s/apps/llm-serving/reasoning.yaml b/k8s/apps/llm-serving/reasoning.yaml
index 0dd677c..19aae96 100644
--- a/k8s/apps/llm-serving/reasoning.yaml
+++ b/k8s/apps/llm-serving/reasoning.yaml
@@ -28,7 +28,8 @@ spec:
       - --quantization=bitsandbytes
       - --dtype=float16
       - --kv-cache-dtype=auto
-      - --tensor-parallel-size=2
+      - --tensor-parallel-size=1
+      - --pipeline-parallel-size=2
       - --max-model-len=16384
       - --gpu-memory-utilization=0.90
       - --max-num-seqs=4