[AMD] Add MiniMax-M3-FP8 MI355X ATOM EAGLE3 / non-EAGLE3 update 0623

.github/configs/amd-master.yaml

@@ -2612,8 +2612,27 @@ minimaxm3-fp4-mi355x-atom:
       - { tp: 4, conc-start: 1, conc-end: 256 }
       - { tp: 8, conc-start: 1, conc-end: 2 }
 
+minimaxm3-fp8-mi355x-atom:
+  image: rocm/atom-dev:MiniMax-M3-20260623
+  model: MiniMaxAI/MiniMax-M3-MXFP8
+  model-prefix: minimaxm3
+  runner: mi355x
+  precision: fp8
+  framework: atom
+  multinode: false
+  scenarios:
+    fixed-seq-len:
+    - isl: 1024
+      osl: 1024
+      search-space:
+      - { tp: 4, conc-start: 1, conc-end: 256 }
+    - isl: 8192
+      osl: 1024
+      search-space:
+      - { tp: 4, conc-start: 1, conc-end: 256 }
+
 minimaxm3-fp8-mi355x-atom-mtp:
-  image: rocm/atom-dev:MiniMax-M3-20260622
+  image: rocm/atom-dev:MiniMax-M3-20260623
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: mi355x

benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom.sh

@@ -0,0 +1,87 @@
+#!/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: $DP_ATTENTION"
+
+SERVER_LOG=/workspace/server.log
+
+PARALLEL_ARGS=(-tp "$TP") #TP
+if [ "$DP_ATTENTION" = "true" ]; then
+    if [ "$EP_SIZE" -gt 1 ]; then #DP+EP
+        PARALLEL_ARGS=(-tp "$TP" --enable-expert-parallel --enable-dp-attention )
+    else #DP+TP
+        PARALLEL_ARGS=(-tp "$TP" --enable-dp-attention )
+    fi
+fi 
+
+SPEC_ARGS=()
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+MEM_FRAC_STATIC=0.8
+
+set -x
+#export AITER_QUICK_REDUCE_QUANTIZATION=INT4
+export ATOM_M3_SPARSE_USE_ASM_PA=1
+export MAX_MODEL_LEN=32768
+export MAX_NUM_BATCHED_TOKENS=32768
+export MAX_NUM_SEQS=256
+python3 -m atom.entrypoints.openai_server \
+    --model $MODEL \
+    --server-port $PORT \
+    "${PARALLEL_ARGS[@]}" \
+    "${SPEC_ARGS[@]}" \
+    --block-size 128 \
+    --gpu-memory-utilization $MEM_FRAC_STATIC \
+    --max-model-len $MAX_MODEL_LEN \
+    --max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
+    --max-num-seqs $MAX_NUM_SEQS \
+    --kv_cache_dtype fp8 \
+    --trust-remote-code \
+    --no-enable_prefix_caching \
+    > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# 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 $( [[ ${#SPEC_ARGS[@]} -gt 0 ]] && echo "--use-chat-template" )
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x

benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_mi355x_atom_mtp.sh

@@ -37,12 +37,11 @@ start_gpu_monitor
 MEM_FRAC_STATIC=0.8
 
 set -x
-export AITER_QUICK_REDUCE_QUANTIZATION=INT4
+#export AITER_QUICK_REDUCE_QUANTIZATION=INT4
+export ATOM_M3_SPARSE_USE_ASM_PA=1
 export MAX_MODEL_LEN=32768
 export MAX_NUM_BATCHED_TOKENS=32768
 export MAX_NUM_SEQS=256
-# (srok), not yet
-#    --kv_cache_dtype fp8 \
 python3 -m atom.entrypoints.openai_server \
     --model $MODEL \
     --server-port $PORT \
@@ -53,6 +52,7 @@ python3 -m atom.entrypoints.openai_server \
     --max-model-len $MAX_MODEL_LEN \
     --max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
     --max-num-seqs $MAX_NUM_SEQS \
+    --kv_cache_dtype fp8 \
     --trust-remote-code \
     --no-enable_prefix_caching \
     > $SERVER_LOG 2>&1 &

perf-changelog.yaml

@@ -4001,6 +4001,13 @@
     - "Remove the runtime SupportsEagle3 source patch now included in the pinned nightly"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1843
 
+- config-keys:
+    - minimaxm3-fp8-mi355x-atom
+  description:
+    - "Add minimaxm3-fp8-mi355x-atom: MiniMax-M3 MXFP8 single-node benchmark on MI355X using ATOM framework"
+    - "Uses rocm/atom-dev:MiniMax-M3-20260623; TP4, block size 128, ISL=1024,8192 OSL=1024"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1929
+
 - config-keys:
     - minimaxm3-fp8-mi355x-atom-mtp
   description: