diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index d3b1b6729..718f95196 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1801,7 +1801,7 @@ dsv4-fp4-b200-vllm-agentic:
       - { tp: 8, ep: 8, dp-attn: true, offloading: cpu,  conc-list: [64, 128, 256] }
 
 dsv4-fp4-b200-trt:
-  image: ghcr.io#semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-9aa3715
+  image: ghcr.io#semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-2dd03e6
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b200-dsv4
@@ -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: ghcr.io#semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-2dd03e6
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_trt.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_trt.sh
index e4a24dea2..f2b19a8cb 100644
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_trt.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b200_trt.sh
@@ -47,6 +47,13 @@ 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: with attention-DP the V2 scheduler grows ctx KV
+# (incl. SWA scratch) before delay batching defers a request, and the resulting
+# revert_allocate_context -> resize(shrink) can't release the scratch of a
+# never-forwarded request (no finish_event), crashing every dpa=true job.
+export TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE="${TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE:-0}"
+echo "TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE: $TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE"
+
 if [[ "$MODEL" != /* ]]; then
     hf download "$MODEL"
 fi
diff --git a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
index b0150e10d..3606c677f 100644
--- a/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
+++ b/benchmarks/single_node/fixed_seq_len/dsv4_fp4_b300_trt.sh
@@ -59,6 +59,13 @@ sanitize_slurm_mpi_env_for_trtllm
 export NCCL_NVLS_ENABLE="${NCCL_NVLS_ENABLE:-0}"
 echo "NCCL_NVLS_ENABLE: $NCCL_NVLS_ENABLE"
 
+# Disable DSv4 SWA scratch reuse: with attention-DP the V2 scheduler grows ctx KV
+# (incl. SWA scratch) before delay batching defers a request, and the resulting
+# revert_allocate_context -> resize(shrink) can't release the scratch of a
+# never-forwarded request (no finish_event), crashing every dpa=true job.
+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 d201e9f3b..17d162518 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3378,6 +3378,13 @@
     - "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-b200-trt
+    - dsv4-fp4-b300-trt
+  description:
+    - "Revert the non-MTP TensorRT-LLM DeepSeek-V4-Pro image to ghcr.io/semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-2dd03e6 and disable DSv4 SWA scratch reuse via TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE=0 in the launcher. Root cause of the prior attention-DP hangs/crashes: the V2 scheduler grows a context request's KV cache (incl. SWA scratch slots) before delay batching can defer it, so revert_allocate_context -> resize(shrink) must release scratch slots of a never-forwarded request, which has no finish_event -> crash on every dpa=true job. Disabling scratch reuse stops those slots from being allocated so the revert shrinks cleanly."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
+
 - config-keys:
     - dsv4-fp4-mi355x-sglang-mtp
   description: