fix: 12 bug fixes from comprehensive review — 51 tok/s verified on RTX 5090

P0 fixes (blocking usability):
- FIX-01: thread-local cuBLAS handle (was creating/destroying per matmul)
- FIX-16: EOS token no longer leaks into API responses
- FIX-17: max_seq_len configurable via --max-seq-len (default 2048, was hardcoded 256)
- FIX-18: max_tokens clamped to available seq space, prompt overflow returns 400

P1 fixes (bugs & performance):
- FIX-07: CachingAllocator wired into all hot paths (to_device, embedding, rope, concat)
- FIX-08: CudaDeviceProp buffer increased to 32KB for CUDA 12.9 safety
- FIX-09: tokenizer byte_fallback graceful degradation (was panic)
- FIX-19: causal mask uses -INFINITY instead of -1e9 (BF16 supports inf)
- FIX-20: LayerNorm rewritten to numerically stable two-pass algorithm
- FIX-21: min block size guard (32 threads) for LayerNorm/RMSNorm launches

P2 fixes (improvements):
- FIX-22: Option<GpuKVCache> + take() eliminates dummy KV cache allocations
- FIX-23: RoPE cache no longer artificially capped at 8192 positions

Verified on dash5 (RTX 5090): 51 tok/s batch=1, 74 tok/s 2-concurrent, 1.7-3.3x HF transformers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-model/src/qwen3.rs

@@ -42,7 +42,7 @@ impl Qwen3 {
         let lm_head_raw = take(&mut w, "lm_head.weight");
 
         let rope_cache = RopeCache::new(
-            config.max_seq_len().min(8192), // limit for memory
+            config.max_seq_len(),
             config.head_dim(),
             config.rope_theta.unwrap_or(1_000_000.0) as f32,
         );
@@ -453,7 +453,7 @@ fn concat_rows(rows: &[Tensor]) -> Tensor {
 
     // Allocate output [B, cols] and copy each row into it
     let total_bytes = batch * row_bytes;
-    let mut out_buf = xserv_cuda::GpuBuffer::alloc(total_bytes).expect("alloc concat_rows");
+    let mut out_buf = xserv_cuda::allocator::cached_alloc(total_bytes).expect("alloc concat_rows");
 
     for (b, row) in rows.iter().enumerate() {
         assert_eq!(row.shape(), &[1, cols]);