quantization: W8A8 FP8 compute via cuBLASLt tensor cores

Replace the W8A16 dequant→BF16-GEMM path with native FP8×FP8→BF16 GEMM
using cuBLASLt on Blackwell (RTX 5090). Both weights (static FP8 E4M3)
and activations (dynamically quantized per-row) are processed directly
on FP8 tensor cores.

Key implementation details:
- cuBLASLt on Blackwell requires transA=T for FP8, so expert weights
  are transposed during model loading ([E,K,N] → [E,N,K])
- Per-row activation quantization kernel (absmax/448 → FP8 E4M3)
- Post-GEMM row-wise rescaling recovers per-token precision
- Per-expert loop (not batched) due to cuBLASLt FP8 scale constraints

The same FP8 quantized model files work — no re-quantization needed.
Activation quantization happens dynamically at inference time.

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

crates/xserv-kernels/build.rs

@@ -8,6 +8,7 @@ fn main() {
     println!("cargo:rustc-link-search=native={cuda_path}/lib64");
     println!("cargo:rustc-link-lib=dylib=cudart");
     println!("cargo:rustc-link-lib=dylib=cublas");
+    println!("cargo:rustc-link-lib=dylib=cublasLt");
 
     cc::Build::new()
         .cuda(true)
@@ -31,6 +32,7 @@ fn main() {
         .file("../../csrc/attention/reshape_and_cache.cu")
         .file("../../csrc/moe/moe_kernels.cu")
         .file("../../csrc/quantization/dequant_fp8.cu")
+        .file("../../csrc/quantization/quantize_fp8.cu")
         .compile("xserv_kernels");
 
     println!("cargo:rerun-if-changed=../../csrc/");