diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 225992f4d..58469dcc4 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -2695,7 +2695,7 @@ minimaxm3-fp4-mi355x-vllm-mtp:
 # https://github.com/ROCm/ATOM/blob/5d42d49f9e4292e5b61475917e92e7ec1b1dacb7/recipes/MiniMax-M3.md
 # block size 128 is mandatory for MSA. TP4 on a single gfx950 node, per the recipe.
 minimaxm3-fp4-mi355x-atom:
-  image: rocm/atom-dev:MiniMax-M3-20260623
+  image: rocm/atom-dev:MiniMax-M3-20260630
   model: amd/MiniMax-M3-MXFP4
   model-prefix: minimaxm3
   runner: mi355x
@@ -2714,7 +2714,7 @@ minimaxm3-fp4-mi355x-atom:
       - { tp: 4, conc-start: 1, conc-end: 256 }
 
 minimaxm3-fp4-mi355x-atom-mtp:
-  image: rocm/atom-dev:MiniMax-M3-20260623
+  image: rocm/atom-dev:MiniMax-M3-20260630
   model: amd/MiniMax-M3-MXFP4
   model-prefix: minimaxm3
   runner: mi355x
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom.sh
index a0907f18c..3cfce7937 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom.sh
@@ -31,6 +31,7 @@ if [ "$DP_ATTENTION" = "true" ]; then
 fi 
 
 SPEC_ARGS=()
+OPT_ARGS=(--online_quant_config '{"global_quant_config": "ptpc_fp8", "exclude_layer": ["lm_head", "model.embed_tokens", "vision_tower", "multi_modal_projector", "patch_merge_mlp", "*block_sparse_moe"]}' --hf-overrides '{"use_index_cache": true, "index_topk_freq": 4}')
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -38,8 +39,7 @@ MEM_FRAC_STATIC=0.8
 
 set -x
 export AITER_QUICK_REDUCE_QUANTIZATION=INT4
-export AITER_QUICK_REDUCE_CAST_BF16_TO_FP16=0
-export ATOM_M3_SPARSE_USE_ASM_PA=1
+export ATOM_FORCE_ATTN_TRITON=1
 export MAX_MODEL_LEN=32768
 export MAX_NUM_BATCHED_TOKENS=32768
 export MAX_NUM_SEQS=256
@@ -48,6 +48,7 @@ python3 -m atom.entrypoints.openai_server \
     --server-port $PORT \
     "${PARALLEL_ARGS[@]}" \
     "${SPEC_ARGS[@]}" \
+    "${OPT_ARGS[@]}" \
     --block-size 128 \
     --gpu-memory-utilization $MEM_FRAC_STATIC \
     --max-model-len $MAX_MODEL_LEN \
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
index fe71c47a0..47de985be 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
@@ -31,6 +31,7 @@ if [ "$DP_ATTENTION" = "true" ]; then
 fi 
 
 SPEC_ARGS=(--method eagle3 --draft-model Inferact/MiniMax-M3-EAGLE3 --num-speculative-tokens 3 )
+OPT_ARGS=(--online_quant_config '{"global_quant_config": "ptpc_fp8", "exclude_layer": ["lm_head", "model.embed_tokens", "vision_tower", "multi_modal_projector", "patch_merge_mlp", "*block_sparse_moe"]}' --hf-overrides '{"use_index_cache": true, "index_topk_freq": 4}')
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -38,8 +39,7 @@ MEM_FRAC_STATIC=0.8
 
 set -x
 export AITER_QUICK_REDUCE_QUANTIZATION=INT4
-export AITER_QUICK_REDUCE_CAST_BF16_TO_FP16=0
-export ATOM_M3_SPARSE_USE_ASM_PA=1
+export ATOM_FORCE_ATTN_TRITON=1
 export MAX_MODEL_LEN=32768
 export MAX_NUM_BATCHED_TOKENS=32768
 export MAX_NUM_SEQS=256
@@ -48,6 +48,7 @@ python3 -m atom.entrypoints.openai_server \
     --server-port $PORT \
     "${PARALLEL_ARGS[@]}" \
     "${SPEC_ARGS[@]}" \
+    "${OPT_ARGS[@]}" \
     --block-size 128 \
     --gpu-memory-utilization $MEM_FRAC_STATIC \
     --max-model-len $MAX_MODEL_LEN \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 66577badb..06586a614 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4352,6 +4352,15 @@
     - "Reuse the existing MXFP8 B300 topology and concurrency matrix across 15 srt-slurm recipes, while dropping the FP8-only Marlin override from TP4 decode"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1966
 
+- config-keys:
+    - minimaxm3-fp4-mi355x-atom
+    - minimaxm3-fp4-mi355x-atom-mtp
+  description:
+    - "Bump image to rocm/atom-dev:MiniMax-M3-20260630 for both fp4 atom entries"
+    - "Add OPT_ARGS: pass --online_quant_config '{\"global_quant_config\": \"ptpc_fp8\", \"exclude_layer\": [\"lm_head\", \"model.embed_tokens\", \"vision_tower\", \"multi_modal_projector\", \"patch_merge_mlp\", \"*block_sparse_moe\"]}' and --hf-overrides '{\"use_index_cache\": true, \"index_topk_freq\": 4}' to both scripts"
+    - "Replace AITER_QUICK_REDUCE_CAST_BF16_TO_FP16=0 and ATOM_M3_SPARSE_USE_ASM_PA=1 with ATOM_FORCE_ATTN_TRITON=1"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1967
+
 - config-keys:
     - minimaxm3-fp8-mi355x-atom
     - minimaxm3-fp8-mi355x-atom-mtp