Update ReadME feature content

[dsikka]

• Updates / extends to include the following pieces:

1. Supported features
2. Benefits of Speculators
3. Summary table of supported models / models that will be supported
4. A point on future features (e.g. training)

[github-actions]

📦 Build Artifacts Available
The build artifacts (`.whl` and `.tar.gz`) have been successfully generated and are available for download: https://github.com/vllm-project/speculators/actions/runs/17409864819/artifacts/3908277154.
They will be retained for up to 30 days.
Commit: 593aff8

[rahul-tuli]

Suggested change

**Speculators** is a unified library for building, evaluating, and storing speculative decoding algorithms for large language model (LLM) inference, including in frameworks like vLLM. Speculative decoding is a lossless technique that speeds up LLM inference by using a smaller, faster speculator model to propose tokens, which are then verified by the larger base model, reducing latency without compromising output quality. Speculators intelligently draft multiple tokens ahead of time, and the main model verifies them in a single step. This approach boosts performance without sacrificing output quality, as every accepted token is guaranteed to match what the main model would have generated on its own. Speculators standardizes this process with reusable formats and tools, enabling easier integration and deployment of speculative decoding in production-grade inference servers.

**Speculators** is a unified library for building, evaluating, and storing speculative decoding algorithms for large language model (LLM) inference, including in frameworks like vLLM. Speculative decoding is a lossless technique that speeds up LLM inference by using a smaller, faster speculator model to propose tokens, which are then verified by the larger base model, reducing latency without compromising output quality. Speculators intelligently draft multiple tokens ahead of time, and the main model verifies them in a single forward pass. This approach boosts performance without sacrificing output quality, as every accepted token is guaranteed to match what the main model would have generated on its own. Speculators standardizes this process with reusable formats and tools, enabling easier integration and deployment of speculative decoding in production-grade inference servers.

[rahul-tuli]

We've used Speculators (the repo) and Speculators (The draft models) both in this sentence, do you feel it might be confusing?

[rahul-tuli]

We've used Speculators (the repo) and Speculators (The draft models) both in this sentence, do you feel it might be confusing?

[rahul-tuli]

Suggested change

	pip install -e .[dev]
	pip install -e ".[dev]"

For supporting zsh as well