diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 3d6a17ff7..e35346198 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/tensorrt-llm/release:1.3.0rc15.post1
   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/tensorrt-llm/release:1.3.0rc15.post1
   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..35ac41f6b 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:-0}"
+echo "TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE: $TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE"
+
 nvidia-smi
 
 SERVER_LOG="$PWD/server.log"
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
index 507b96e34..f6ac67d6b 100644
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt_mtp.sh
@@ -58,6 +58,11 @@ sanitize_slurm_mpi_env_for_trtllm
 export NCCL_NVLS_ENABLE="${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:-0}"
+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 d69f528a8..212e70dc3 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3387,6 +3387,13 @@
     - "Add MTP speculative-decoding sibling for dsv4-fp4-mi355x-vllm (model: deepseek-ai/DeepSeek-V4-Pro) on vllm/vllm-openai-rocm:v0.22.0, per vllm-project/vllm#43385"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1630
 
+- config-keys:
+    - dsv4-fp4-b300-trt
+    - dsv4-fp4-b300-trt-mtp
+  description:
+    - "Point the B300 TensorRT-LLM DeepSeek-V4-Pro configs (non-MTP dsv4-fp4-b300-trt and MTP dsv4-fp4-b300-trt-mtp) at the official NVIDIA release image nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc15.post1, replacing the custom ghcr.io semianalysis feat/deepseek_v4 builds (2dd03e6 and 9aa3715 respectively), to evaluate the official RC for DeepSeek-V4-Pro. Also drops the TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE=0 launcher workaround (specific to the custom build) so the official image runs with its native behavior. B200 TRT is unchanged (stays on feat-deepseek_v4-9aa3715)."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
+
 - config-keys:
     - dsv4-fp4-mi355x-sglang-mtp
   description:
@@ -3445,6 +3452,13 @@
     - "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:
     - minimaxm2.5-fp8-gb300-dynamo-vllm
   description: