From 8e0dfbf3dd485710dd6a149b57a2161125b34aac Mon Sep 17 00:00:00 2001
From: seungrokj <seungrok.jung@amd.com>
Date: Thu, 16 Apr 2026 08:27:26 +0000
Subject: [PATCH 1/3] atom glm5 fp4 on mi355x

Signed-off-by: seungrokj <seungrok.jung@amd.com>
---
 .../single_node/glm5_fp4_mi355x_atom.sh       | 81 +++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 benchmarks/single_node/glm5_fp4_mi355x_atom.sh

diff --git a/benchmarks/single_node/glm5_fp4_mi355x_atom.sh b/benchmarks/single_node/glm5_fp4_mi355x_atom.sh
new file mode 100644
index 000000000..31bc8b25f
--- /dev/null
+++ b/benchmarks/single_node/glm5_fp4_mi355x_atom.sh
@@ -0,0 +1,81 @@
+#!/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
+pip install -U transformers
+python3 -m atom.entrypoints.openai_server \
+    --model $MODEL \
+    --server-port $PORT \
+    -tp $TP \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
+    --default-chat-template-kwargs '{"enable_thinking": false}' \
+    --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" 
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x

From 5c565eec429b56fa362efe88e9abb2e2e8c57647 Mon Sep 17 00:00:00 2001
From: seungrokj <seungrok.jung@amd.com>
Date: Thu, 16 Apr 2026 08:30:55 +0000
Subject: [PATCH 2/3] atom glm5 fp4 on mi355x

Signed-off-by: seungrokj <seungrok.jung@amd.com>
---
 .github/configs/amd-master.yaml | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 89318004b..990c34692 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -277,6 +277,28 @@ glm5-fp8-mi355x-atom:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 256 }
 
+glm5-fp4-mi355x-atom:
+  #TODO
+  image: TBD
+  model: zai-org/GLM-5-FP8
+  model-prefix: glm5
+  runner: mi355x
+  precision: fp4
+  framework: atom
+  multinode: false
+  seq-len-configs:
+  #TODO:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 256 }
+    - { tp: 8, conc-start: 4, conc-end: 256 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 256 }
+    - { tp: 8, conc-start: 4, conc-end: 256 }
+
 kimik2.5-int4-mi355x-vllm:
   image: vllm/vllm-openai-rocm:v0.18.0
   model: moonshotai/Kimi-K2.5

From a3b84c8878eee931030d9c69c1357343918fe38f Mon Sep 17 00:00:00 2001
From: seungrokj <seungrok.jung@amd.com>
Date: Thu, 16 Apr 2026 08:35:11 +0000
Subject: [PATCH 3/3] atom glm5 fp4 on mi355x

Signed-off-by: seungrokj <seungrok.jung@amd.com>
---
 .github/configs/amd-master.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 990c34692..efa2d7416 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -280,7 +280,7 @@ glm5-fp8-mi355x-atom:
 glm5-fp4-mi355x-atom:
   #TODO
   image: TBD
-  model: zai-org/GLM-5-FP8
+  model: amd/GLM-5.1-MXFP4
   model-prefix: glm5
   runner: mi355x
   precision: fp4