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-tokenizer/src/bpe.rs

@@ -51,8 +51,6 @@ impl Tokenizer {
         let tj: TokenizerJson = serde_json::from_str(&data)
             .unwrap_or_else(|e| panic!("failed to parse tokenizer.json: {e}"));
 
-        let byte_fallback = tj.model.byte_fallback;
-
         // Build encoder: token bytes → ID
         // All HF tokenizers use GPT-2 byte-to-unicode mapping for vocab keys.
         let mut encoder = HashMap::new();
@@ -170,16 +168,25 @@ impl Tokenizer {
             }
             // Fall back to per-byte encoding
             let word_bytes: Vec<u8> = word.bytes().collect();
-            let mut token_ids: Vec<u32> = word_bytes.iter().map(|&b| {
+            let mut token_ids: Vec<u32> = word_bytes.iter().filter_map(|&b| {
                 if let Some(&id) = self.encoder.get(&vec![b]) {
-                    id
+                    Some(id)
                 } else if self.byte_fallback {
                     let hex_token = format!("<0x{:02X}>", b);
-                    *self.special_tokens.get(&hex_token).unwrap_or_else(|| {
-                        panic!("byte 0x{b:02X} not in vocab and no fallback token {hex_token}")
-                    })
+                    if let Some(&id) = self.special_tokens.get(&hex_token) {
+                        Some(id)
+                    } else if let Some(&id) = self.encoder.get(hex_token.as_bytes()) {
+                        Some(id)
+                    } else if let Some(&unk_id) = self.special_tokens.get("<unk>") {
+                        eprintln!("warning: byte 0x{b:02X} not in vocab, using <unk> token");
+                        Some(unk_id)
+                    } else {
+                        eprintln!("warning: byte 0x{b:02X} not in vocab and no fallback token, using token 0");
+                        Some(0)
+                    }
                 } else {
-                    panic!("byte {b} (0x{b:02X}) not in vocab")
+                    eprintln!("warning: byte {b} (0x{b:02X}) not in vocab, skipping");
+                    None
                 }
             }).collect();