SpecDec Bench: February Update (#875)

**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->

**Overview:**
Addition of SpecBench Dataset
Addition of NVIDID SPEED-Bench dataset, preproc scripts, and custom
metrics aggregator
Addition of example of converting SpecBench Medusa to this FW
Addition of Initial TRTLLM AutoDeploy Specdec support

Updates to all frameworks for better perf (overlap/async scheduling etc)

<!-- You can potentially add a usage example below. -->

```python
```

<!-- Mention how have you tested your change if applicable. -->

<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->

- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->

<!-- E.g. related issue. -->

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

* **New Features**
* Added SPEED-Bench dataset support with configurable throughput and
qualitative configurations
* Introduced SpecBench metrics with acceptance rate analysis and
visualizations
  * Added progress bar during benchmark execution
* New model implementations for auto-deployment and Medusa-style
speculative decoding
  * Data preparation utility for benchmark datasets
  * Enhanced metrics with per-category analysis and performance charts

* **Documentation**
  * Updated README with SPEED-Bench workflow and examples
  * New porting guide for integrating custom benchmark runners

* **Refactor**
  * Streamlined model and runner interfaces for improved flexibility
* Consolidated dataset implementations and removed deprecated base
classes

* **Chores**
  * Added required dependencies for data handling and visualizations

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Signed-off-by: Izzy Putterman <iputterman@nvidia.com>

Author: IzzyPutterman

examples/specdec_bench/README.md

@@ -28,17 +28,121 @@ MTBench is available [here](https://huggingface.co/datasets/HuggingFaceH4/mt_ben
 Download `nvidia/gpt-oss-120b-Eagle3` to a local directory `/path/to/eagle`.
 
 ```bash
-python3 run.py --model_dir openai/gpt-oss-120b --tokenizer openai/gpt-oss-120b --draft_model_dir /path/to/eagle --mtbench question.jsonl --tp_size 1 --ep_size 1 --draft_length 3 --output_length 4096 --num_requests 80 --engine TRTLLM --concurrency 1 --postprocess gptoss
-
+python3 run.py \
+    --model_dir openai/gpt-oss-120b \
+    --tokenizer openai/gpt-oss-120b \
+    --draft_model_dir /path/to/eagle \
+    --mtbench question.jsonl \
+    --tp_size 1 \
+    --ep_size 1 \
+    --draft_length 3 \
+    --output_length 4096 \
+    --num_requests 80 \
+    --engine TRTLLM \
+    --concurrency 1 \
+    --postprocess gptoss
 ```
 
 ### Running Random ids on GPT OSS + Eagle3
 
 Download `nvidia/gpt-oss-120b-Eagle3` to a local directory `/path/to/eagle`.
 
 ```bash
-python3 run.py --model_dir openai/gpt-oss-120b --tokenizer openai/gpt-oss-120b --draft_model_dir /path/to/eagle --random_isl 1024 --tp_size 1 --ep_size 1 --draft_length 3 --output_length 4096 --num_requests 40 --engine TRTLLM --concurrency 1
+python3 run.py \
+    --model_dir openai/gpt-oss-120b \
+    --tokenizer openai/gpt-oss-120b \
+    --draft_model_dir /path/to/eagle \
+    --random_isl 1024 \
+    --tp_size 1 \
+    --ep_size 1 \
+    --draft_length 3 \
+    --output_length 4096 \
+    --num_requests 40 \
+    --engine TRTLLM \
+    --concurrency 1
+```
+
+### Running [SPEED-Bench](https://huggingface.co/datasets/nvidia/SPEED-Bench) on Llama 3.3 70B + Eagle 3
+
+1. Install the requirements file using `pip install -r requirements_speed.txt`
+
+2. Prepare the data using the provided script:
+
+```bash
+python3 prepare_data.py --dataset speed --config all
+```
+
+The data will be saved to `data/` directory, each config type (qualitative, throughput_1k, ...) to each own directory.
+
+#### License
+
+GOVERNING TERMS: This dataset is governed by the NVIDIA Evaluation Dataset License Agreement.
+
+ADDITIONAL INFORMATION: MIT for bigcode/humanevalpack, RUCAIBox/MMATH, RUCAIBox/BAMBOO and EQ-Bench. Apache 2.0 for Writing Bench and Spec-Bench. CC BY 4.0 for FBK-MT/MCIF. MIT and Apache 2.0 for tianyang/repobench_python_v1.1, JetBrains-Research/lca-project-level-code-completion and tianyang/repobench_java_v1.1.
+
+NOTICE: For each dataset a user elects to use, the user is responsible for checking if the dataset license is fit for the intended purpose. The `prepare_data.py` script automatically fetches data from all the source datasets.
+
+Additional details are in [HuggingFace dataset repository](https://huggingface.co/datasets/nvidia/SPEED-Bench).
+
+#### Qualitative split
+
+```bash
+python3 run.py \
+    --model_dir meta-llama/Llama-3.3-70B-Instruct \
+    --tokenizer meta-llama/Llama-3.3-70B-Instruct \
+    --draft_model_dir yuhuili/EAGLE3-LLaMA3.3-Instruct-70B \
+    --dataset speed \
+    --dataset_path data/speed/qualitative \
+    --tp_size 8 \
+    --ep_size 1 \
+    --draft_length 3 \
+    --output_length 4096 \
+    --engine TRTLLM \
+    --concurrency 32 \
+    --show_progress
+```
+
+#### Throughput split
 
+```bash
+python3 run.py \
+    --model_dir meta-llama/Llama-3.3-70B-Instruct \
+    --tokenizer meta-llama/Llama-3.3-70B-Instruct \
+    --draft_model_dir yuhuili/EAGLE3-LLaMA3.3-Instruct-70B \
+    --dataset speed \
+    --dataset_path data/speed/throughput_1k \
+    --tp_size 8 \
+    --ep_size 1 \
+    --draft_length 3 \
+    --output_length 4096 \
+    --engine TRTLLM \
+    --concurrency 32 \
+    --show_progress
+```
+
+For longer context (>8192 tokens), please use the following configuration when using TRTLLM:
+
+```yaml
+engine_args:
+  max_seq_len: 131072   # Model max context length (for Llama 3.3 70B)
+  enable_chunked_prefill: true
+```
+
+```bash
+python3 run.py \
+    --model_dir meta-llama/Llama-3.3-70B-Instruct \
+    --tokenizer meta-llama/Llama-3.3-70B-Instruct \
+    --draft_model_dir yuhuili/EAGLE3-LLaMA3.3-Instruct-70B \
+    --dataset speed \
+    --dataset_path data/speed/throughput_16k \
+    --tp_size 8 \
+    --ep_size 1 \
+    --draft_length 3 \
+    --output_length 4096 \
+    --engine TRTLLM \
+    --concurrency 32 \
+    --show_progress \
+    --runtime_params runtime_args_long_context.yaml
 ```
 
 ## Notes