init v0.23.0

Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>
2026-08-27 15:11:51 +08:00
parent b582a8e7d1
commit 7f8a1b1f7a
2849 changed files with 712887 additions and 22001 deletions
--- a/tests/e2e/nightly/single_node/models/configs/Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml
@@ -0,0 +1,78 @@
+# ==========================================
+# ACTUAL TEST CASES
+# ==========================================
+
+test_cases:
+  - name: "prefix-cache-deepseek-r1-0528-w8a8"
+    model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
+    envs:
+      OMP_NUM_THREADS: "10"
+      OMP_PROC_BIND: "false"
+      HCCL_BUFFSIZE: "1024"
+      PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+      SERVER_PORT: "DEFAULT_PORT"
+      VLLM_ENGINE_READY_TIMEOUT_S: "7200"
+    server_cmd:
+      - "--quantization"
+      - "ascend"
+      - "--data-parallel-size"
+      - "2"
+      - "--tensor-parallel-size"
+      - "8"
+      - "--enable-expert-parallel"
+      - "--port"
+      - "$SERVER_PORT"
+      - "--seed"
+      - "1024"
+      - "--max-model-len"
+      - "5200"
+      - "--max-num-batched-tokens"
+      - "4096"
+      - "--max-num-seqs"
+      - "16"
+      - "--trust-remote-code"
+      - "--gpu-memory-utilization"
+      - "0.9"
+      - "--additional-config"
+      - '{"enable_weight_nz_layout": true}'
+      - "--speculative-config"
+      - '{"num_speculative_tokens": 1, "method": "mtp"}'
+    test_content:
+      - "benchmark_comparisons"
+    benchmark_comparisons_args:
+      - metric: "TTFT"
+        baseline: "prefix0"
+        target: "prefix75"
+        ratio: 0.5
+        operator: "<"
+    benchmarks:
+      warm_up:
+        case_type: performance
+        dataset_path: vllm-ascend/GSM8K-in1024-bs210
+        request_conf: vllm_api_stream_chat
+        dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+        num_prompts: 210
+        max_out_len: 1
+        batch_size: 1000
+        baseline: 0
+        threshold: 0.97
+      prefix0:
+        case_type: performance
+        dataset_path: vllm-ascend/prefix0-in3500-bs210
+        request_conf: vllm_api_stream_chat
+        dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+        num_prompts: 210
+        max_out_len: 1
+        batch_size: 18
+        baseline: 1
+        threshold: 0.97
+      prefix75:
+        case_type: performance
+        dataset_path: vllm-ascend/prefix75-in3500-bs210
+        request_conf: vllm_api_stream_chat
+        dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+        num_prompts: 210
+        max_out_len: 1
+        batch_size: 18
+        baseline: 1
+        threshold: 0.97