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..dfb1e7a9f 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"]}')
 
 # 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 $MAX_MODEL_LEN \
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
index fe71c47a0..4ef60e71e 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_mi355x_atom_mtp.sh
@@ -31,6 +31,7 @@ if [ "$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"]}')
 
 # 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 $MAX_MODEL_LEN \
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom.sh
index 3506a3764..c5ce072fc 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom.sh
@@ -31,6 +31,7 @@ if [ "$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"]}')
 
 # 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 $MAX_MODEL_LEN \
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom_mtp.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom_mtp.sh
index a5b019b80..66320d03d 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom_mtp.sh
@@ -31,6 +31,7 @@ if [ "$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"]}')
 
 # 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/configs/amd-master.yaml b/configs/amd-master.yaml
index 95a76ab6d..41f60afda 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -2645,7 +2645,7 @@ 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:nightly_202607011530
   model: amd/MiniMax-M3-MXFP4
   model-prefix: minimaxm3
   runner: mi355x
@@ -2664,7 +2664,7 @@ 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:nightly_202607011530
   model: amd/MiniMax-M3-MXFP4
   model-prefix: minimaxm3
   runner: mi355x
@@ -2683,7 +2683,7 @@ minimaxm3-fp4-mi355x-atom-mtp:
       - { tp: 4, conc-start: 1, conc-end: 256, spec-decoding: mtp  }
 
 minimaxm3-fp8-mi355x-atom:
-  image: rocm/atom-dev:MiniMax-M3-20260623
+  image: rocm/atom-dev:nightly_202607011530
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: mi355x
@@ -2702,7 +2702,7 @@ minimaxm3-fp8-mi355x-atom:
       - { tp: 4, conc-start: 1, conc-end: 256 }
 
 minimaxm3-fp8-mi355x-atom-mtp:
-  image: rocm/atom-dev:MiniMax-M3-20260623
+  image: rocm/atom-dev:nightly_202607011530
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: mi355x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6eb6ca61f..3944e67c5 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4422,3 +4422,14 @@
     - "Update Minimax M3 b200 vllm image tag"
     - "Update search space to cover more configs"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1978
+
+- config-keys:
+    - minimaxm3-fp4-mi355x-atom
+    - minimaxm3-fp4-mi355x-atom-mtp
+    - minimaxm3-fp8-mi355x-atom
+    - minimaxm3-fp8-mi355x-atom-mtp
+  description:
+    - "Bump ATOM image from rocm/atom-dev:MiniMax-M3-20260623 to rocm/atom-dev:nightly_202607011530 for all single-node MiniMax-M3 ATOM recipes."
+    - "Add --online_quant_config with ptpc_fp8 and MoE layer exclusions (*block_sparse_moe) to all scripts."
+    - "Replace deprecated 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/2001