diff --git a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/b200-fp4-mtp/agentic.yaml b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/b200-fp4-mtp/agentic.yaml
index 36bba702cb..65551cf4ae 100644
--- a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/b200-fp4-mtp/agentic.yaml
+++ b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/b200-fp4-mtp/agentic.yaml
@@ -6,7 +6,7 @@ base:
   name: dsv4-fp4-b200-sglang-agentic
   model:
     path: hf:deepseek-ai/DeepSeek-V4-Pro-0813
-    container: lmsysorg/sglang:v0.5.19-cu130
+    container: lmsysorg/sglang:v0.5.20-cu130
     precision: fp4
   resources:
     gpu_type: b200
@@ -85,7 +85,7 @@ override_tp8_c1:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 2
-        cuda-graph-max-bs: 2
+        cuda-graph-max-bs-decode: 2
   benchmark:
     env:
       CONC: '1'
@@ -100,7 +100,7 @@ override_tp8_c2:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 4
-        cuda-graph-max-bs: 4
+        cuda-graph-max-bs-decode: 4
   benchmark:
     env:
       CONC: '2'
@@ -115,7 +115,7 @@ override_tp8_c3:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 6
-        cuda-graph-max-bs: 6
+        cuda-graph-max-bs-decode: 6
   benchmark:
     env:
       CONC: '3'
@@ -130,7 +130,7 @@ override_tp8_c4:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 8
-        cuda-graph-max-bs: 8
+        cuda-graph-max-bs-decode: 8
   benchmark:
     env:
       CONC: '4'
@@ -145,7 +145,7 @@ override_tp8_c5:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 10
-        cuda-graph-max-bs: 10
+        cuda-graph-max-bs-decode: 10
   benchmark:
     env:
       CONC: '5'
@@ -160,7 +160,7 @@ override_tp8_hicache_c8:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 16
-        cuda-graph-max-bs: 16
+        cuda-graph-max-bs-decode: 16
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -181,7 +181,7 @@ override_tp8_hicache_c10:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 20
-        cuda-graph-max-bs: 20
+        cuda-graph-max-bs-decode: 20
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -202,7 +202,7 @@ override_tp8_hicache_c16:
         swa-full-tokens-ratio: 0.1
         chunked-prefill-size: 8192
         max-running-requests: 32
-        cuda-graph-max-bs: 32
+        cuda-graph-max-bs-decode: 32
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -246,7 +246,7 @@ override_dep8_hicache_c64:
         swa-full-tokens-ratio: 0.02
         chunked-prefill-size: 49152
         max-running-requests: 128
-        cuda-graph-max-bs: 32
+        cuda-graph-max-bs-decode: 32
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -294,7 +294,7 @@ override_dep8_hicache_c96:
         swa-full-tokens-ratio: 0.02
         chunked-prefill-size: 49152
         max-running-requests: 192
-        cuda-graph-max-bs: 32
+        cuda-graph-max-bs-decode: 32
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -342,7 +342,7 @@ override_dep8_hicache_c128:
         swa-full-tokens-ratio: 0.02
         chunked-prefill-size: 49152
         max-running-requests: 256
-        cuda-graph-max-bs: 32
+        cuda-graph-max-bs-decode: 32
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
@@ -391,7 +391,7 @@ override_dep8_hicache_c160:
         swa-full-tokens-ratio: 0.02
         chunked-prefill-size: 49152
         max-running-requests: 320
-        cuda-graph-max-bs: 32
+        cuda-graph-max-bs-decode: 32
         enable-hierarchical-cache: true
         hicache-write-policy: write_through
         hicache-io-backend: direct
diff --git a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv41flash/vllm/mi355x-fp4-mtp/agentic.yaml b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv41flash/vllm/mi355x-fp4-mtp/agentic.yaml
index 9ab84be6dd..fc67c49e8b 100644
--- a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv41flash/vllm/mi355x-fp4-mtp/agentic.yaml
+++ b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv41flash/vllm/mi355x-fp4-mtp/agentic.yaml
@@ -6,7 +6,7 @@ base:
   name: dsv41flash-fp4-mi355x-vllm-agentic
   model:
     path: hf:deepseek-ai/DeepSeek-V4.1-Flash
-    container: vllm/vllm-openai-rocm:nightly-rocm100-7f1a5398e9610d96c473931a26c0e12bbe0d0423
+    container: vllm/vllm-openai-rocm:nightly-rocm100-29468dde8b515031dc6d4d9d06bf0a2fa0442098
     precision: fp4
   resources:
     gpu_type: mi355x
diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml
index 9b9c48a0ef..9c337b0f72 100644
--- a/inferencex-e2e/perf-changelog.yaml
+++ b/inferencex-e2e/perf-changelog.yaml
@@ -9168,3 +9168,17 @@
     - "Relevant ATOM changes in the range: V4 decode reuses the sparse prefill ASM (ROCm/ATOM#2271), greedy sampler picks via aiter.topk_select (ROCm/ATOM#2244), and FP8 block scales declared scale_fmt ue8m0 are now stored as E8M0 on gfx950 by default (ROCm/ATOM#2419; previously FP32 unless ATOM_FP8_BLOCKSCALE_USE_E8M0_SCALE=1). The upstream DeepSeek-V4 recipes are unchanged across the range, and every recipe flag and choice (all2all-backend rccl, dp-load-balance least_tokens, moe-backend standard) remains valid."
     - "No data-type or precision change to the DeepSeek-V4-Pro-0813 DSpark draft: no online quantization is configured, so it keeps its checkpoint precision; the E8M0 scale storage represents the checkpoint's power-of-two block scales exactly. kv-cache-dtype and index-cache-dtype touch cache storage only."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3605
+
+- config-keys:
+    - dsv41flash-fp4-mi355x-vllm-agentic-dspark
+    - dsv4-fp4-b200-sglang-agentic-hicache-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Align the single-node srt-slurm recipe model.container with the unchanged master image for two AgentX keys whose recipes #3428 ported from the legacy scripts as they were before the image bumps in #3420 and #3334; every point of these keys would fail before submission with 'Single-node SRT image: recipe/matrix'."
+    - "Recipe containers: dsv41flash-fp4-mi355x-vllm-agentic-dspark vllm/vllm-openai-rocm:nightly-rocm100-7f1a5398e9610d96c473931a26c0e12bbe0d0423 -> vllm/vllm-openai-rocm:nightly-rocm100-29468dde8b515031dc6d4d9d06bf0a2fa0442098; dsv4-fp4-b200-sglang-agentic-hicache-mtp lmsysorg/sglang:v0.5.19-cu130 -> lmsysorg/sglang:v0.5.20-cu130."
+    - "The B200 SGLang v0.5.20 recipe also renames cuda-graph-max-bs to cuda-graph-max-bs-decode, as #3334 did in the legacy script, because v0.5.20 removed the deprecated alias (sgl-project/sglang#38375). All other serving flags and sweep points are unchanged."
+    - "将两个 AgentX key 的单节点 srt-slurm 配方 model.container 与未改动的主配置镜像对齐。这些配方由 #3428 从旧脚本移植而来，而移植所依据的是 #3420 和 #3334 升级镜像之前的版本；此前这些 key 的每个点都会在提交前以 'Single-node SRT image: recipe/matrix' 失败。"
+    - "配方镜像：dsv41flash-fp4-mi355x-vllm-agentic-dspark vllm/vllm-openai-rocm:nightly-rocm100-7f1a5398e9610d96c473931a26c0e12bbe0d0423 -> vllm/vllm-openai-rocm:nightly-rocm100-29468dde8b515031dc6d4d9d06bf0a2fa0442098；dsv4-fp4-b200-sglang-agentic-hicache-mtp lmsysorg/sglang:v0.5.19-cu130 -> lmsysorg/sglang:v0.5.20-cu130。"
+    - "B200 的 SGLang v0.5.20 配方同时将 cuda-graph-max-bs 改为 cuda-graph-max-bs-decode，与 #3334 对旧脚本的修改一致，因为 v0.5.20 已移除该弃用别名（sgl-project/sglang#38375）。其余服务参数和 sweep 点均保持不变。"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3567