diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 0cbe0e8c8f..56f866865e 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -7624,10 +7624,10 @@ qwen3.5-fp4-gb200-dynamo-sglang-agentic-mtp:
           - "CONFIG_FILE=recipes/sglang/qwen3.5/gb200-fp4/agentic/agg-gb200-tp2ep2-mtp-hicache.yaml"
 
 minimaxm3-fp4-b300-vllm-agentic-mtp:
-  image: vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45
+  image: vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c
   model: nvidia/MiniMax-M3-NVFP4
   model-prefix: minimaxm3
-  runner: cluster:b300-nv
+  runner: cluster:b300-dsxe
   precision: fp4
   framework: vllm
   multinode: false
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 4fcd229bfb..8ac5dcf095 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6958,3 +6958,13 @@
     - "Expand the TP8 and TP4/EP1 sweep coverage through concurrency 640."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2866
   
+
+- config-keys:
+    - minimaxm3-fp4-b300-vllm-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Update vLLM image from vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45 (2026-08-30 nightly) to vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly, digest sha256:254eebf919e8b7b0d530d97fccc606c36f380ff6724d64bc190951bec1aee838, tag commit vllm-project/vllm@d9105ea8; Docker Hub last pushed 2026-09-07T06:16:01Z), the same tag the B200/H100/H200 MiniMax-M3 AgentX recipes moved to in #2860/#2874/#2875. benchmarks/single_node/agentic/minimaxm3_fp4_b300_mtp.sh is unchanged: EAGLE3 with the Inferact MiniMax-M3 EAGLE3-GQA draft on FLASH_ATTN, golden synthetic acceptance length 2.78, fp8 KV, max-cudagraph-capture-size 512; the TP8/TP4/TP2 grids with vllm-simple DRAM offload are unchanged."
+    - "Move the recipe from the retired cluster:b300-nv fleet (launcher and runner labels removed in #2826) to cluster:b300-dsxe so the sweep has a runner to schedule on. The runner change means this is not an append-only bump: the whole curve reruns on DSXE."
+    - "Re-pin from vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly) to vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c (2026-09-04 nightly, digest sha256:f5df5cc3302b5f404848c4eca88d7bf7ed5226e151c056da22816d7734644d67; Docker Hub last pushed 2026-09-04T06:18:14Z, tag commit vllm-project/vllm@8a728663). Nightlies from 2026-09-05 onward carry vllm-project/vllm@4ee259551 (Sync FA with upstream, #54819), which moves vllm-flash-attn to 506341a1; on Blackwell the EAGLE3 draft runs FLASH_ATTN through the FA4 CuTe path and, with the fp8 KV cache, its descale tensors now fail to_cute_tensor with RuntimeError: Expected strides[leading_dim] == 1, but got 0 during CUDA-graph memory profiling, so the engine never starts (B200 run 34168437161). The 2026-09-04 nightly is the newest build still on vllm-flash-attn 06bdd47c, the same FA pin as the recipe's previous 2026-08-30 image, and the same vllm commit the MI355X MiniMax-M3 vLLM AgentX recipe already runs (nightly-8a728663). No vllm fix has landed on main as of 2026-09-08T03:00Z."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2883