diff --git a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_atom_mtp.sh
index 764e40e46..13155407d 100644
--- a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_atom_mtp.sh
@@ -129,6 +129,13 @@ esac
 export ATOM_ENABLE_REPLAYSSM
 export AITER_REUSE_IDENTICAL_COMM_GROUPS
 
+# From concurrency 16 up, hold a ready prefill for 4 decode passes instead of
+# interleaving it into every step; MAX_QUEUE_MS bounds the wait. 14 runs without it.
+if [ "$CONC" -ge 16 ]; then
+    export ATOM_PREFILL_DECODE_INTERVAL=4
+    export ATOM_PREFILL_DELAYER_MAX_QUEUE_MS=5000
+fi
+
 # Full CUDA graphs over [1 .. window * (1 + draft tokens)]: the verify step
 # submits one row per draft token on top of the accepted token, so capturing
 # only up to the window would send every speculative decode down the eager path.
@@ -199,6 +206,8 @@ export AITER_FLYDSL_STAGE2_FP8=1
 # costs more in evictions than its reuse is worth on these traces.
 export ATOM_STATE_CHECKPOINT_DEMAND=0
 export ATOM_GDN_SSM_DTYPE=fp16
+# FlyDSL FP8 prefill attention; ATOM defaults it off.
+export ATOM_USE_FLYDSL_FP8_PREFILL_ATTN=1
 
 # https://github.com/SemiAnalysisAI/InferenceX/blob/main/golden_al_distribution/kimik3_dspark_probabilistic_sample_method_block_rejection_sample_method.yaml
 #  7 draft tokens -> AL 3.84
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index 543c40458..c771f07db 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -690,7 +690,7 @@ kimik3-fp4-mi355x-vllm-agentic-mtp:
 #            wider in-flight window needs the deeper pool to keep the paged KV
 #            resident.
 kimik3-fp4-mi355x-atom-agentic-mtp:
-  image: rocm/atom-dev:ubuntu24.04_py3.12_pytorch_release_2.10.0_kimi_k3_agentic_0911
+  image: rocm/atom-dev:nightly_202609251613
   model: moonshotai/Kimi-K3
   model-prefix: kimik3
   runner: cluster:mi355x-amds
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 1bc132cd3..b6108908a 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -8950,3 +8950,14 @@
   description:
     - "Update SGLang image from v0.5.19-cu130 to v0.5.20-cu130 and pass --cuda-graph-max-bs-decode after the alias removal."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3334
+
+- config-keys:
+    - kimik3-fp4-mi355x-atom-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Move the MI355X Kimi-K3 FP4 ATOM AgentX submission to image rocm/atom-dev:ubuntu24.04_py3.12_pytorch_release_2.10.0_kimi_k3_agentic_0924, tracking recipes/Agentic-Kimi-K3.md as retuned in ROCm/ATOM#2382."
+    - "Enable FlyDSL FP8 prefill attention (ATOM_USE_FLYDSL_FP8_PREFILL_ATTN=1) on every concurrency; ATOM defaults it off."
+    - "Hold a ready prefill for four decode passes from concurrency 16 up (ATOM_PREFILL_DECODE_INTERVAL=4, ATOM_PREFILL_DELAYER_MAX_QUEUE_MS=5000). Concurrency 1, 4 and 14 are unchanged."
+    - "Keep the published concurrency set [1, 4, 14, 16, 48, 56, 72], max-num-seqs, max-num-batched-tokens, gpu-memory-utilization, the CUDA-graph ladder, dcp-size, draft depth, synthetic acceptance, ReplaySSM placement and LMCache sizing unchanged."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3407