feat(demos,inference): wire simulation demos to real compute; fix embedding lookup and weight-name aliases

Demos:
- rtx-distllm-demo: real rtx-tensor weights per shard, real
  scaled-dot-product attention forward, metrics measured (Instant)
  instead of hardcoded constants; network topology remains a documented
  simulation fed by real tensor byte sizes.
- rtx-model-zoo: MockInferenceEngine deleted; RealInferenceEngine loads
  a tiny real transformer into rtx_inference::InferenceEngine and runs
  genuine engine.infer per request; domain outputs are explicitly-
  labeled toy proxies derived from real output tokens.
- rtx-inference-profiler: mock models deleted; profiles real
  matmul/softmax pipelines on rtx-tensor with measured latency/memory.

Inference-path bugs the demos surfaced (fixed here):
- ForwardPass::apply_embedding misused Tensor::gather for the embedding
  lookup — gather returns the indices' shape, silently dropping the
  hidden dim and breaking every downstream broadcast. Now uses the
  existing Tensor::embedding_lookup ([vocab,hidden] x [batch,seq] ->
  [batch,seq,hidden]).
- Attention weight lookup accepts both self_attn. (HF-LLaMA) and
  attention. prefixes; final layer norm accepts norm.weight /
  model.norm.weight / ln_f.weight aliases.
- Integration fixture gains the final norm weight; the previously
  always-failing engine tests now pass (8/8 model_loading_test).

End-to-end inference through the real engine now works for the first
time — verified via model_zoo_demo producing real forward-pass outputs
across all categories.

Co-Authored-By: Claude Fable 5 <[email protected]>

demos/rtx-distllm-demo/src/bin/distllm_demo.rs

@@ -0,0 +1,26 @@
+//! Runnable entry point for the DistributedLLM demo.
+//!
+//! Prints the `InferenceResult` from `rtx_distllm_demo::run_demo()`,
+//! including real measured latencies from actual tensor compute (attention
+//! matmul/softmax) mixed with the simulated network/tokenizer pieces
+//! documented in `rtx_distllm_demo`'s crate-level docs.
+
+fn main() {
+    let result = rtx_distllm_demo::run_demo();
+
+    println!("=== DistributedLLM Demo ===");
+    println!("Prompt tokens:      {}", result.prompt_tokens);
+    println!("Completion tokens:  {}", result.completion_tokens);
+    println!("Finish reason:      {:?}", result.finish_reason);
+    println!();
+    println!("Total latency (ms):        {:.3}", result.latency_ms);
+    println!("Time to first token (ms):  {:.3}", result.time_to_first_token_ms);
+    println!("Tokens/sec:                {:.3}", result.tokens_per_second);
+    println!(
+        "Per-token latencies (ms):  {:?}",
+        &result.token_latencies_ms[..result.token_latencies_ms.len().min(10)]
+    );
+    println!();
+    println!("Generated text:");
+    println!("{}", result.text);
+}