fix issues

qwen3_6_scripts/patch_ops.sh

@@ -8,8 +8,6 @@
 #     are already correct for standard Triton 2.3.1 — do NOT overwrite them.
 #   - DO NOT install BI-V150 corex Triton 2.1.0 (pkgs/triton): that causes
 #     GPU hang on BI-V100 because the Triton CUDA PTX kernels are incompatible.
-#
-# Important Note: Qwen3.6-27B must apply TP=4,PP=2 combination in order to deploy using 8 GPUs
 
 # Recommended server start command for TP=4 support 100K, need chunked prefill
 # CUDA_VISIBLE_DEVICES="4,5,6,7" VLLM_ENGINE_ITERATION_TIMEOUT_S=3600 python3 -m vllm.entrypoints.openai.api_server \
@@ -17,6 +15,14 @@
 #     --max-model-len 100000 --enforce-eager --trust-remote-code -tp 4 --gpu-memory-utilization 0.95 \
 #     --max-num-seqs 1 --disable-log-requests --disable-frontend-multiprocessing \
 #     --max-num-batched-tokens 4096 --enable-chunked-prefill
+#
+# With prefix caching (GDN align-mode, requires chunked prefill):
+# CUDA_VISIBLE_DEVICES="4,5,6,7" VLLM_ENGINE_ITERATION_TIMEOUT_S=3600 python3 -m vllm.entrypoints.openai.api_server \
+#     --model /workspace/models/Qwen3.6-35B-A3B --port 1111 --served-model-name llm \
+#     --max-model-len 150000 --trust-remote-code -tp 4 --gpu-memory-utilization 0.90 \
+#     --max-num-seqs 1 --disable-log-requests --disable-frontend-multiprocessing \
+#     --max-num-batched-tokens 8192 --enable-chunked-prefill --enable-prefix-caching \
+#     --max-seq-len-to-capture 32768
 
 # --- paged_attn.py: replace forward_prefix with pure-PyTorch fallback -------
 # The Triton context_attention_fwd kernel hangs BI-V100 GPUs permanently
@@ -26,6 +32,15 @@
 # when context length is high
 cp ./paged_attn.py /usr/local/corex/lib/python3/dist-packages/vllm/attention/ops/paged_attn.py
 
+# --- model_runner.py: fix prefix_cache_hit stays True in chunked-prefill chunk 2+ ---
+# Bug: _compute_for_prefix_cache_hit Case 1 (prefix_cache_len <= context_len)
+# leaves prefix_cache_hit=True. Then _add_seq_group uses block_table=computed_block_nums
+# (only the original prefix blocks), ignoring chunk-1 KV cache blocks.
+# _forward_prefix_pytorch then gets an undersized block_tables and crashes with
+# "amax(): Expected reduction dim -1 to have non-zero size" on the 2nd tile.
+# Fix: set prefix_cache_hit=False for Case 1 so the full block_tables is used.
+python3 ./patch_model_runner.py
+
 # --- transformers: Qwen3_5 tokenizer / model files --------------------------
 pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple
 cp -r ./qwen3_5 /usr/local/lib/python3.10/site-packages/transformers/models/
@@ -42,8 +57,15 @@ python3 ./patch_vllm_qwen3_5.py
 # returns _cached_all_token_ids[-0:] == [0:] (the ENTIRE prompt+output list).
 # Each prefill chunk step adds prompt_len to previous_num_tokens, so a 10K
 # prompt processed in 3 chunks inflates completion_tokens by ~30K.
+# Also adds num_cached_tokens field to RequestMetrics for prefix-cache stats.
 cp ./sequence.py /usr/local/corex/lib/python3/dist-packages/vllm/sequence.py
 
+# --- scheduler.py: record num_cached_tokens in RequestMetrics ----------------
+# Sets seq_group.metrics.num_cached_tokens = prefix_cache_len on first prefill
+# when --enable-prefix-caching is active, so serving_chat.py can report it in
+# usage.prompt_tokens_details.cached_tokens (OpenAI-compatible API response).
+cp ./scheduler.py /usr/local/corex/lib/python3/dist-packages/vllm/core/scheduler.py
+
 # --- xformers: bypass cudnnFlashAttnForward (head_dim=256 > 128 limit) ------
 # Injects _run_sdpa_fallback (pure matmul+softmax) into xformers.py.
 # Required because head_dim=256 > 128 and ixformer flash attention either