[DEPLOY] Complete submission: baseline + all optimizations

Adds ALL files needed for Dockerfile build:
  - qwen3_6_scripts/ (baseline patches + our optimizations)
  - vllm/ (full vllm package)
  - paged_attention_v2_pytorch.py (V2 with single-bmm optimization)
  - Dockerfile + computility-run.yaml

Our optimizations vs baseline:
  1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls),
     Triton try/fallback, V2 heuristic, threshold 32K→64K
  2. paged_attention_v2_pytorch.py: fills NotImplementedError,
     single-bmm Phase 1 (195 launches → 3)
  3. patch_enable_triton.py: HAS_TRITON=True with safety fallback
  4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100
  5. computility-run.yaml: gpu-memory-utilization 0.9→0.95,
     max-num-batched-tokens 8192→16384

This repo can now be submitted to dev.modelhub.org.cn as-is.

vllm/entrypoints/logger.py

@@ -0,0 +1,42 @@
+from typing import List, Optional, Union
+
+from vllm.logger import init_logger
+from vllm.lora.request import LoRARequest
+from vllm.pooling_params import PoolingParams
+from vllm.prompt_adapter.request import PromptAdapterRequest
+from vllm.sampling_params import BeamSearchParams, SamplingParams
+
+logger = init_logger(__name__)
+
+
+class RequestLogger:
+
+    def __init__(self, *, max_log_len: Optional[int]) -> None:
+        super().__init__()
+
+        self.max_log_len = max_log_len
+
+    def log_inputs(
+        self,
+        request_id: str,
+        prompt: Optional[str],
+        prompt_token_ids: Optional[List[int]],
+        params: Optional[Union[SamplingParams, PoolingParams,
+                               BeamSearchParams]],
+        lora_request: Optional[LoRARequest],
+        prompt_adapter_request: Optional[PromptAdapterRequest],
+    ) -> None:
+        max_log_len = self.max_log_len
+        if max_log_len is not None:
+            if prompt is not None:
+                prompt = prompt[:max_log_len]
+
+            if prompt_token_ids is not None:
+                prompt_token_ids = prompt_token_ids[:max_log_len]
+
+        logger.info(
+            "Received request %s: prompt: %r, "
+            "params: %s, prompt_token_ids: %s, "
+            "lora_request: %s, prompt_adapter_request: %s.", request_id,
+            prompt, params, prompt_token_ids, lora_request,
+            prompt_adapter_request)