diff --git a/.github/workflows/run-sweep.yml b/.github/workflows/run-sweep.yml
index fe77ba1010..a7a3ef2e97 100644
--- a/.github/workflows/run-sweep.yml
+++ b/.github/workflows/run-sweep.yml
@@ -536,7 +536,7 @@ jobs:
             model-prefix: ${{ matrix.config.model-prefix }}
             framework: ${{ matrix.config.framework }}
             precision: ${{ matrix.config.precision }}
-            conc-list: '[${{ matrix.config.conc }}]'
+            conc-list: ${{ toJson(matrix.config.conc) }}
             spec-decoding: ${{ matrix.config.spec-decoding }}
             disagg: ${{ matrix.config.disagg }}
             prefill-hardware: ${{ matrix.config.prefill.hardware }}
@@ -551,7 +551,7 @@ jobs:
             decode-ep: ${{ matrix.config.decode.ep }}
             decode-dp-attn: ${{ matrix.config.decode.dp-attn }}
             decode-additional-settings: ${{ toJson(matrix.config.decode.additional-settings) }}
-            conc: ${{ matrix.config.conc }}
+            conc: ${{ matrix.config.conc[0] }}
             kv-offloading: ${{ matrix.config.kv-offloading }}
             kv-offload-backend: ${{ matrix.config.kv-offload-backend }}
             duration: ${{ matrix.config.duration }}
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/agentic/disagg-gb200-3p2d-tep8-tp8-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/agentic/disagg-gb200-3p2d-tep8-tp8-agentic.yaml
index 9e2b665843..b1f22f1d23 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/agentic/disagg-gb200-3p2d-tep8-tp8-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/agentic/disagg-gb200-3p2d-tep8-tp8-agentic.yaml
@@ -110,7 +110,11 @@ backend:
       # FULL capture conflicts with NCCL symmetric-memory registration on the
       # TP prefill path; PIECEWISE preserves compilation and safe graph regions.
       compilation-config: '{"cudagraph_mode":"PIECEWISE"}'
-      gpu-memory-utilization: 0.9
+      # 0.9 leaves <1 GiB free per GPU on the TEP8 prefill workers and both
+      # sweep attempts died to serving-time transients (sparse-indexer logits
+      # alloc at c64, DeepGEMM JIT module load at c4). MLA KV is compact, so
+      # trading KV space for allocator headroom costs prefill nothing.
+      gpu-memory-utilization: 0.85
       no-disable-hybrid-kv-cache-manager: true
       tokenizer-mode: deepseek_v4
     decode:
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 0cf684364e..3e98cc3a3b 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4643,3 +4643,12 @@
     - "Recipes sourced from NVIDIA/srt-slurm branch sa-submission-q2-2026 (gb300_nvfp4 MTP recipes)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1799
 
+- config-keys:
+    - dsv4-fp4-gb200-dynamo-vllm-agentic-3p2d-tep8-tp8
+    - dsv4-fp4-gb200-dynamo-vllm-agentic-2p1d-dep8-dep8
+  description:
+    - "Full agentic-coding sweep of the DSv4 FP4 GB200 dynamo-vllm disagg topologies on the June 21 AgentX corpus"
+    - "3p2d TEP8 prefill / TP8 decode (40 inference GPUs): c4-c80"
+    - "2p1d DEP8 prefill / DEP8 decode (24 inference GPUs): c32-c256 including exploratory tail past the c160 normalized-throughput peak"
+    - "Lower 3p2d prefill gpu-memory-utilization 0.9 -> 0.85: both first-pass attempts OOMed on prefill serving-time transients (sparse-indexer logits at c64, DeepGEMM JIT at c4) with <1 GiB free per GPU"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2122