di ci: glm-5-2 1p 1d

Author: Yu

.github/benchmark/models_atomesh.yaml

@@ -107,6 +107,51 @@ models:
       fewshot: 3
       limit: null
 
+  GLM-5.2-FP8:
+    backend: atom
+    model_path: "${ATOMESH_MODEL_ROOT}/GLM-5.2-FP8/"
+    precision: FP8
+    env:
+      common: {}
+      prefill: {}
+      decode: {}
+    server:
+      common_args:
+        trust_remote_code: true
+        kv_cache_dtype: fp8
+        block_size: 16
+        gpu_memory_utilization: 0.8
+        max_model_len: 32768
+        max_num_seqs: 256
+        max_num_batched_tokens: 32768
+        extra_args: ""
+    suites:
+      nightly:
+        - name: glm-5-2-fp8-1p1d-tp8
+          topology: 1p1d
+          pd_worker_layout: multi_node
+          nodes: "${ATOMESH_1P1D_NODES}"
+          isl: [8192]
+          osl: 1024
+          concurrency: [1, 2, 4, 8, 16, 32, 64, 128, 256]
+          prefill:
+            workers: 1
+            tp: 8
+          decode:
+            workers: 1
+            tp: 8
+          benchmark:
+            wait_server_timeout: 4200
+          runner:
+            time_limit: "08:00:00"
+          run_eval: true
+          eval_concurrency: [64, 256]
+
+    accuracy:
+      task: gsm8k
+      fewshot: 3
+      limit: null
+
   Kimi-K2.5-MXFP4:
     backend: atom
     model_path: "${ATOMESH_MODEL_ROOT}/Kimi-K2.5-MXFP4/"

.github/workflows/atomesh-benchmark.yaml

@@ -42,6 +42,11 @@ on:
         required: false
         default: false
         type: boolean
+      run_glm_5_2_fp8:
+        description: 'Run GLM-5.2-FP8'
+        required: false
+        default: false
+        type: boolean
       run_kimi_k25_mxfp4:
         description: 'Run Kimi-K2.5-MXFP4'
         required: false
@@ -152,6 +157,7 @@ jobs:
           SUITE: ${{ (github.event_name == 'schedule' || github.event_name == 'push') && 'nightly' || (github.event_name == 'workflow_dispatch' && inputs.suite || 'smoke') }}
           RUN_ALL_MODELS: ${{ github.event_name == 'workflow_dispatch' && inputs.run_all_models || github.event_name != 'workflow_dispatch' }}
           RUN_DEEPSEEK_V4_PRO: ${{ github.event_name == 'workflow_dispatch' && inputs.run_deepseek_v4_pro || false }}
+          RUN_GLM_5_2_FP8: ${{ github.event_name == 'workflow_dispatch' && inputs.run_glm_5_2_fp8 || false }}
           RUN_KIMI_K25_MXFP4: ${{ github.event_name == 'workflow_dispatch' && inputs.run_kimi_k25_mxfp4 || false }}
           RUN_MINIMAX_M3_MXFP4: ${{ github.event_name == 'workflow_dispatch' && inputs.run_minimax_m3_mxfp4 || false }}
           RUN_MINIMAX_M3_MXFP8: ${{ github.event_name == 'workflow_dispatch' && inputs.run_minimax_m3_mxfp8 || false }}
@@ -164,6 +170,7 @@ jobs:
           if [[ "${GITHUB_EVENT_NAME}" == "workflow_dispatch" && "${RUN_ALL_MODELS}" != "true" ]]; then
             selected_models=()
             [[ "${RUN_DEEPSEEK_V4_PRO}" == "true" ]] && selected_models+=("DeepSeek-V4-Pro")
+            [[ "${RUN_GLM_5_2_FP8}" == "true" ]] && selected_models+=("GLM-5.2-FP8")
             [[ "${RUN_KIMI_K25_MXFP4}" == "true" ]] && selected_models+=("Kimi-K2.5-MXFP4")
             [[ "${RUN_MINIMAX_M3_MXFP4}" == "true" ]] && selected_models+=("MiniMax-M3-MXFP4")
             [[ "${RUN_MINIMAX_M3_MXFP8}" == "true" ]] && selected_models+=("MiniMax-M3-MXFP8")