Skip to content

feat: add fasttokens benchmarks and tokenizer backend docs#7388

Open
biswapanda wants to merge 3 commits intobis/fast-tokens-dynamofrom
bis/fast-tokens-bench-docs
Open

feat: add fasttokens benchmarks and tokenizer backend docs#7388
biswapanda wants to merge 3 commits intobis/fast-tokens-dynamofrom
bis/fast-tokens-bench-docs

Conversation

@biswapanda
Copy link
Contributor

@biswapanda biswapanda commented Mar 14, 2026

Overview:

Benchmarks:

  • Rename benches/tokenizer.rs to benches/tokenizer_simple.rs, add criterion fasttokens vs HF encode and batch-encode benchmarks
  • Add benches/tokenizer_dataset.rs: dataset-driven benchmark using LongBench-v2 (503 real-world samples), sequential and batched modes with correctness verification (~24x sequential, ~27x batched speedup)

Docs:

  • docs/components/frontend/tokenizer-backends.md: user guide with configuration, compatibility notes, and benchmark results
  • docs/components/frontend/configuration.md: added Tokenizer section
  • docs/index.yml: added Tokenizer Backends page under Frontend

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

@biswapanda biswapanda requested a review from a team as a code owner March 14, 2026 21:54
@github-actions github-actions bot added feat documentation Improvements or additions to documentation labels Mar 14, 2026
@github-actions
Copy link
Contributor

github-actions bot commented Mar 14, 2026

@biswapanda biswapanda requested review from dagil-nvidia and nealvaidya and removed request for a team March 14, 2026 21:57
Copy link
Contributor

@nealvaidya nealvaidya left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approving from docs standpoint

Benchmarks:
- Rename benches/tokenizer.rs to benches/tokenizer_simple.rs, add
  criterion fasttokens vs HF encode and batch-encode benchmarks
- Add benches/tokenizer_dataset.rs: dataset-driven benchmark using
  LongBench-v2 (503 real-world samples), sequential and batched modes
  with correctness verification (~24x sequential, ~27x batched speedup)

Docs:
- docs/components/frontend/tokenizer-backends.md: user guide with
  configuration, compatibility notes, and benchmark results
- docs/components/frontend/configuration.md: added Tokenizer section
- docs/index.yml: added Tokenizer Backends page under Frontend
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation feat size/L

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants