feat: Implement BitNet inference stack — TL1 kernel, backend, GGUF export, RLM refiner

Phase 0 + 0.5 implementation (4,283 lines across 6 new files):

- tl1_kernel.rs (879L): TL1 ternary GEMV with NEON SIMD + scalar fallback,
  INT8 activation quantization (absmax), LUT generation, 17 tests
- backend.rs (1,179L): Full BitNetBackend implementing LlmBackend trait,
  GGUF model loading, MoE router (softmax gate + top-K), expert FFN
  (SwiGLU via TL1 GEMV), RMSNorm, embedding/LM head, 12 tests
- gguf_export.rs (662L): GGUF v3 writer for BITNET_T158, FP16 conversion,
  model export with BitNet metadata, validation, 8 tests
- rlm_refiner.rs (696L): Phase 0.5 orchestrator wiring MicroLoRA + EWC++ +
  GRPO + ContrastiveTrainer, SIMD-only mode (AD-20), checkpointing, 10 tests
- tl1_avx2.rs (414L): AVX2 SIMD kernel variant (x86_64 conditional)
- tl1_wasm.rs (453L): WASM SIMD128 kernel variant (wasm32 conditional)

All 72 bitnet tests pass. Fixed 2 pre-existing compilation errors in
autodetect.rs and kernels/mod.rs.

https://claude.ai/code/session_011nTcGcn49b8YKJRVoh4TaK

Author: claude

crates/ruvllm/Cargo.toml

@@ -115,6 +115,7 @@ async-runtime = ["tokio", "tokio-stream"]
 # Minimal build without inference (for embedding/library use only)
 minimal = ["async-runtime"]
 wasm = []
+wasm-simd = []
 
 # Ruvector integration features
 attention = ["dep:ruvector-attention"]

crates/ruvllm/src/autodetect.rs

@@ -432,16 +432,8 @@ impl GpuCapabilities {
             return Self::detect_webgpu();
         }
 
-        #[cfg(not(any(
-            target_os = "macos",
-            target_os = "ios",
-            target_os = "linux",
-            target_os = "windows",
-            target_arch = "wasm32"
-        )))]
-        {
-            None
-        }
+        #[allow(unreachable_code)]
+        None
     }
 
     /// Detect Metal GPU capabilities