diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index e24ec38c0..aa7997fe8 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -3049,7 +3049,7 @@ dsv4-fp4-b300-vllm-agentic:
       - { tp: 8, ep: 8, dp-attn: true, offloading: cpu,  conc-list: [128, 256, 512] }
 
 dsv4-fp4-b300-trt:
-  image: ghcr.io#semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-9aa3715
+  image: nvcr.io#nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
@@ -3072,7 +3072,7 @@ dsv4-fp4-b300-trt:
       - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 1024 }
 
 dsv4-fp4-b300-trt-mtp:
-  image: ghcr.io#semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-9aa3715
+  image: nvcr.io#nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
index b0150e10d..0589cc3a6 100644
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
@@ -59,6 +59,11 @@ sanitize_slurm_mpi_env_for_trtllm
 export NCCL_NVLS_ENABLE="${NCCL_NVLS_ENABLE:-0}"
 echo "NCCL_NVLS_ENABLE: $NCCL_NVLS_ENABLE"
 
+# Disable DSv4 SWA scratch reuse to test whether the rc15.post1 DPA crash
+# is the same SWA-scratch bug or a separate FMHA kernel issue.
+export TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE="${TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE:-1}"
+echo "TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE: $TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE"
+
 nvidia-smi
 
 SERVER_LOG="$PWD/server.log"
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
index 507b96e34..8141ff43f 100644
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
@@ -58,6 +58,11 @@ sanitize_slurm_mpi_env_for_trtllm
 export NCCL_NVLS_ENABLE="${NCCL_NVLS_ENABLE:-0}"
 echo "NCCL_NVLS_ENABLE: $NCCL_NVLS_ENABLE"
 
+# Disable DSv4 SWA scratch reuse to test whether the rc15.post1 DPA crash
+# is the same SWA-scratch bug or a separate FMHA kernel issue.
+export TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE="${TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE:-1}"
+echo "TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE: $TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE"
+
 nvidia-smi
 
 SERVER_LOG="$PWD/server.log"
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 47cfcebc1..2d4213854 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3445,6 +3445,13 @@
     - "Add 1k1k/8k1k minimax recipe set under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1641
 
+- config-keys:
+    - dsv4-fp4-b300-trt
+    - dsv4-fp4-b300-trt-mtp
+  description:
+    - "Switch B300 DSv4 TRT (non-MTP + MTP) to official rc15.post1 image with TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE=0 to test whether DPA crash is same SWA-scratch bug"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
+
 - config-keys:
     - dsv4-fp4-b200-vllm
   description:
@@ -3502,3 +3509,10 @@
     - "Update GPT-OSS model for MI355X vLLM from amd/gpt-oss-120b-w-mxfp4-a-fp8 to openai/gpt-oss-120b"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1670
 
+- config-keys:
+    - dsv4-fp4-b300-trt
+    - dsv4-fp4-b300-trt-mtp
+  description:
+    - "Switch B300 DSv4 TRT (non-MTP + MTP) image from rc15.post1 to nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
+