GLM-5.3 sampling example

examples/api/README.md

@@ -10,5 +10,6 @@ These JSON files demonstrate individual Cortex Training request bodies:
 | `fwd-bwd.json` | Submit a readable forward/backward batch |
 | `generate.json` | Submit prompts for generation |
 | `glm-sampling.json` | Create a GLM sampling sub-job |
+| `glm-5.3-sampling.json` | Create a GLM-5.3 sampling sub-job with an fp8 KV cache and a reasoning parser |
 
 They are wire-format examples, not end-to-end training recipes.

examples/api/glm-5.3-sampling.json

@@ -0,0 +1,18 @@
+{
+  "sub_job_configs": [
+    {
+      "inference_config": {
+        "max_seq_len": 32768,
+        "n_gpus": 8,
+        "vllm_config": {
+          "gpu_memory_utilization": 0.85,
+          "kv_cache_dtype": "fp8",
+          "reasoning_parser": "glm45",
+          "tensor_parallel_size": 8
+        }
+      },
+      "job_type": "sampling",
+      "model_name": "zai-org/GLM-5.3"
+    }
+  ]
+}