diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index b9560803e..2ea215fbe 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -293,6 +293,28 @@ glm5-fp8-mi355x-sglang:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+glm5-fp8-mi355x-atom:
+  image: TBD
+  model: zai-org/GLM-5-FP8
+  model-prefix: glm5
+  runner: mi355x
+  precision: fp8
+  framework: atom
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+
 kimik2.5-int4-mi355x-vllm:
   image: vllm/vllm-openai-rocm:v0.18.0
   model: moonshotai/Kimi-K2.5
@@ -363,6 +385,31 @@ kimik2.5-fp4-mi355x-vllm:
     - { tp: 8, conc-start: 4, conc-end: 64 }
     - { tp: 4, conc-start: 4, conc-end: 64 }
 
+kimik2.5-fp4-mi355x-atom:
+  image: TBD
+  model: amd/Kimi-K2.5-MXFP4
+  model-prefix: kimik2.5
+  runner: mi355x
+  precision: fp4
+  framework: atom
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+
 minimaxm2.5-fp8-mi355x-vllm:
   image: vllm/vllm-openai-rocm:v0.18.0
   model: MiniMaxAI/MiniMax-M2.5
@@ -391,6 +438,34 @@ minimaxm2.5-fp8-mi355x-vllm:
     - { tp: 4, conc-start: 4, conc-end: 64 }
     - { tp: 8, ep: 8, conc-start: 32, conc-end: 256 }
 
+minimaxm2.5-fp8-mi355x-atom:
+  image: TBD
+  model: MiniMaxAI/MiniMax-M2.5
+  model-prefix: minimaxm2.5
+  runner: mi355x
+  precision: fp8
+  framework: atom
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 2, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 8, ep: 8, conc-start: 32, conc-end: 256 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 2, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 8, ep: 8, conc-start: 32, conc-end: 256 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 2, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 8, ep: 8, conc-start: 32, conc-end: 256 }
+
 minimaxm2.5-fp8-mi300x-vllm:
   image: vllm/vllm-openai-rocm:v0.16.0
   model: MiniMaxAI/MiniMax-M2.5
diff --git a/benchmarks/single_node/glm5_fp8_mi355x_atom.sh b/benchmarks/single_node/glm5_fp8_mi355x_atom.sh
new file mode 100644
index 000000000..960363bb6
--- /dev/null
+++ b/benchmarks/single_node/glm5_fp8_mi355x_atom.sh
@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE \
+    DP_ATTENTION
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+echo "TP: $TP, CONC: $CONC, ISL: $ISL, OSL: $OSL, EP_SIZE: $EP_SIZE, DP_ATTENTION: $DP_ATTENTION"
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+export OMP_NUM_THREADS=1
+
+# Calculate max-model-len based on ISL and OSL
+if [ "$ISL" = "1024" ] && [ "$OSL" = "1024" ]; then
+    CALCULATED_MAX_MODEL_LEN=""
+else
+    CALCULATED_MAX_MODEL_LEN=" --max-model-len 10240 "
+fi
+
+if [ "$EP_SIZE" -gt 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+
+python3 -m atom.entrypoints.openai_server \
+    --model $MODEL \
+    --server-port $PORT \
+    -tp $TP \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
+    --trust-remote-code \
+    > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+export PYTHONDONTWRITEBYTECODE=1
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/benchmarks/single_node/kimik2.5_fp4_mi355x_atom.sh b/benchmarks/single_node/kimik2.5_fp4_mi355x_atom.sh
new file mode 100644
index 000000000..8f94c3829
--- /dev/null
+++ b/benchmarks/single_node/kimik2.5_fp4_mi355x_atom.sh
@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE \
+    DP_ATTENTION
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+echo "TP: $TP, CONC: $CONC, ISL: $ISL, OSL: $OSL, EP_SIZE: $EP_SIZE, DP_ATTENTION: $DP_ATTENTION"
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+export OMP_NUM_THREADS=1
+
+# Calculate max-model-len based on ISL and OSL
+if [ "$ISL" = "1024" ] && [ "$OSL" = "1024" ]; then
+    CALCULATED_MAX_MODEL_LEN=""
+else
+    CALCULATED_MAX_MODEL_LEN=" --max-model-len 10240 "
+fi
+
+if [ "$EP_SIZE" -gt 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+
+python3 -m atom.entrypoints.openai_server \
+    --model $MODEL \
+    --server-port $PORT \
+    -tp $TP \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
+    --trust-remote-code \
+    > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+export PYTHONDONTWRITEBYTECODE=1
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/benchmarks/single_node/minimaxm2.5_fp8_mi355x_atom.sh b/benchmarks/single_node/minimaxm2.5_fp8_mi355x_atom.sh
new file mode 100644
index 000000000..8f94c3829
--- /dev/null
+++ b/benchmarks/single_node/minimaxm2.5_fp8_mi355x_atom.sh
@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE \
+    DP_ATTENTION
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+echo "TP: $TP, CONC: $CONC, ISL: $ISL, OSL: $OSL, EP_SIZE: $EP_SIZE, DP_ATTENTION: $DP_ATTENTION"
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+export OMP_NUM_THREADS=1
+
+# Calculate max-model-len based on ISL and OSL
+if [ "$ISL" = "1024" ] && [ "$OSL" = "1024" ]; then
+    CALCULATED_MAX_MODEL_LEN=""
+else
+    CALCULATED_MAX_MODEL_LEN=" --max-model-len 10240 "
+fi
+
+if [ "$EP_SIZE" -gt 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+
+python3 -m atom.entrypoints.openai_server \
+    --model $MODEL \
+    --server-port $PORT \
+    -tp $TP \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
+    --trust-remote-code \
+    > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+export PYTHONDONTWRITEBYTECODE=1
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6a8a6e666..610c4ef96 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1108,3 +1108,12 @@
   description:
     - "Update vLLM image from v0.15.1 to v0.18.0 for gptoss H100 and H200 configs"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/960
+
+- config-keys:
+    - kimik2.5-fp4-mi355x-atom
+    - glm5-fp8-mi355x-atom
+    - minimaxm2.5-fp8-mi355x-atom
+  description:
+    - "New model support on ATOM framework"
+    - "Kimi-K2.5 FP4, GLM-5 FP8, and MiniMax-M2.5 FP8 configs added for MI355X ATOM"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/963