fix(crash): disable corex_gdn_chunk_recurrent — pybind signature mismatch

The .so's torch_chunk_gated_delta_rule() only accepts positional args:
  (Tensor, Tensor, Tensor, Tensor, Tensor, int, Optional[Tensor], bool, bool)
But Python calls it with keyword args:
  (q, k, v, g, beta, initial_state=, output_final_state=, use_qk_l2norm_in_kernel=)

This causes 'incompatible function arguments' crash during profiling
(determine_num_available_blocks), killing the engine before it starts.

Fix: _HAS_COREX_GDN_CHUNK = False, forcing Python _torch_chunk_gated_delta_rule.
This is what a3c45d3b effectively did (its .so wasn't compiled), explaining
why a3c45d3b works but aa4b4992 crashes.

qwen3_6_scripts/patch_block_major_worker_capacity.py

@@ -21,11 +21,12 @@ CAPACITY_REPLACEMENT = """\
         num_gpu_blocks = reserve_block_major_gpu_blocks(
             num_gpu_blocks, cache_block_size)
         # BI100: profiling with zero-tensor attention underestimates memory.
-        # Hardcap at 5000 blocks (80K tokens) to prevent runtime OOM.
-        if num_gpu_blocks > 5000:
+        # Hardcap at 3000 blocks (48K tokens) to prevent runtime OOM.
+        # Must leave ~4GB free for flash_attn_varlen_func temp buffers.
+        if num_gpu_blocks > 3000:
             logger.warning(
-                "[BI100] capping num_gpu_blocks: %d -> 5000", num_gpu_blocks)
-            num_gpu_blocks = 5000
+                "[BI100] capping num_gpu_blocks: %d -> 3000", num_gpu_blocks)
+            num_gpu_blocks = 3000
         num_gpu_blocks = max(num_gpu_blocks, 0)
         num_cpu_blocks = max(num_cpu_blocks, 0)
 """

qwen3_6_scripts/qwen3_5.py

@@ -153,7 +153,11 @@ try:
 except ImportError:
     _corex_gdn_chunk_recurrent = None
 
-_HAS_COREX_GDN_CHUNK = _corex_gdn_chunk_recurrent is not None
+# DISABLED: corex_gdn_chunk_recurrent.so pybind uses positional args only,
+# but the call site passes keyword args (initial_state=, output_final_state=).
+# This causes "incompatible function arguments" crash during profiling.
+# Force Python fallback until .so signature is fixed.
+_HAS_COREX_GDN_CHUNK = False
 
 from vllm.model_executor.models.interfaces import (HasInnerState, SupportsLoRA,
                                                    SupportsMultiModal)