litellm/.github/workflows/codspeed.yml
devin-ai-integration[bot] 0abd9267c1
feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174)
* ci: benchmark and gate an installed release wheel

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* ci: simplify installed-wheel benchmark check

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(rust): add native tokenizer codec

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(tokenizer): route Python tokenization through the Rust extension

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style(lint): format tokenizer call

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(packaging): restore runtime dependencies and native images

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(tokenizer): preserve Python SDK behavior with Rust tokenizers

* fix(tokenizer): restore compatibility paths

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(tokenizer): count custom tokenizers directly

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(tokenizer): preserve caller-supplied Python tokenizer counts

* fix(tokenizer): reuse packaged vocabularies in the native wheel

* refactor(rust_bridge): route token counting through the catalog as RUST_OPT_IN

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(spend_tracking): compare tokenizer groups by value

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore(deps): re-resolve filelock under the <4.0 pin

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(llms): align transformation override signatures with base configs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* build(rust): use fat LTO to keep the native wheel under the 35 MB limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(tokenizer): preserve Python defaults with opt-in Rust dispatch

* test(proxy): tolerate missing litellm.utils.Tokenizer when patching it

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): patch the tokenizer dispatch function instead of the removed alias

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(tokenizer): give the Rust wrappers the tiktoken and tokenizers surface

Callers of litellm.encoding and litellm.create_tokenizer must see the same
read-only API whichever backend the catalog selects.

- OpenAIEncoding mirrors tiktoken.Encoding: n_vocab, max_token_value,
  token_byte_values, encode_single_token, encode_with_unstable,
  encode_to_numpy, decode_with_offsets, is_special_token, repr; the Rust
  tiktoken crate keeps a Vocabulary beside each CoreBPE and reports the
  requested encoding name (gpt2 stays gpt2).
- HuggingFaceTokenizer mirrors the read-only tokenizers.Tokenizer surface
  (token_to_id, id_to_token, get_vocab, get_vocab_size,
  get_added_tokens_decoder, num_special_tokens_to_add, padding, truncation,
  encode_special_tokens, from_buffer); HuggingFaceEncoding gains the
  char/word/token lookups, pad, truncate, set_sequence_id and merge.
  Mutators stay on the Python tokenizer.
- from_json/from_pretrained claim the fork gate only when the huggingface
  feature is compiled in; the surrogate fallback matches on the Codec.
- Tokenizer caching is keyed on the same catalog Context the dispatch runs
  on; rust_tokenizer reads the encoding name without loading an encoding;
  LITELLM_RUST parsing is cached.
- Drop the unused tiktoken_encoding_for_model export and Error::Download.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(tokenizer): close the exhaustive matches with assert_never

CodeQL reads a `match` over a Literal with no default arm as an implicit
`None` return. `assert_never` makes the exhaustiveness explicit for both the
HuggingFace tokenizer loader and the Rust token-counter factory.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* feat(tokenizer): derive the fast counter from the shared tokenizer

The count-only counter (`fast` feature) and the codec each parsed the same
artifact: TokenCounter took the Anthropic JSON and the tiktoken rank files
from Python while Tokenizer loaded them again. One parse now serves both.

- FastTokenizer builds from a model another loader holds: `from_shared`
  takes the Arc<tokenizers::Tokenizer> the HF codec keeps, and
  `from_*_pairs` take the ranks the tiktoken vocabulary already parsed.
- `FastCounter::fast_counter` in the core crate derives it from either codec;
  encodings the fast scanner does not reproduce are refused.
- Native `Tokenizer.count(text, fast=False)` opts into that counter, built
  once per tokenizer on first use; `TokenCounter.from_tokenizer(tokenizer,
  fast=False)` replaces the JSON and rank-file constructors.
- The Python route counts over the native tokenizers the codec path shares
  (`native_encoding`, `native_anthropic`) and no longer reads rank files;
  the packaged Anthropic tokenizer has one loader, `tokenizer_dispatch.anthropic`.
- Public wrappers gain `count(text, fast=False)`.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-22 04:41:11 +00:00

100 lines
3.1 KiB
YAML

name: CodSpeed Benchmarks
on:
push:
branches:
- main
- litellm_internal_staging
paths:
- "litellm/**"
- "tests/benchmarks/**"
- "pyproject.toml"
- "uv.lock"
- ".github/workflows/codspeed.yml"
- ".github/actions/setup-uv-with-retries/**"
- ".github/actions/cache-cargo-build/**"
- ".github/scripts/uv_sync_with_retries.sh"
pull_request:
branches:
- main
- litellm_internal_staging
paths:
- "litellm/**"
- "tests/benchmarks/**"
- "pyproject.toml"
- "uv.lock"
- ".github/workflows/codspeed.yml"
- ".github/actions/setup-uv-with-retries/**"
- ".github/actions/cache-cargo-build/**"
- ".github/scripts/uv_sync_with_retries.sh"
# Allow CodSpeed to trigger backtest performance analysis
# in order to generate initial data
workflow_dispatch:
permissions:
contents: read
id-token: write
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
benchmarks:
runs-on: ubuntu-24.04
timeout-minutes: 60
steps:
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: "3.12"
- name: Set up uv
uses: ./.github/actions/setup-uv-with-retries
with:
version: "0.10.9"
- name: Cache the Rust build
uses: ./.github/actions/cache-cargo-build
with:
profile: release
# Build the wheel and resolve every dependency outside the CodSpeed
# runner: the same maturin build took 42 minutes inside `codspeed run`
# versus under 3 minutes as a plain step (LIT-6183)
- name: Build the release wheel
run: uv build --wheel --out-dir dist
- name: Install the wheel into the benchmark environment
run: |
UV_PROJECT_ENVIRONMENT="${RUNNER_TEMP}/benchmark-venv" .github/scripts/uv_sync_with_retries.sh --frozen --no-default-groups --group benchmarks --no-install-project --python 3.12
uv pip install --python "${RUNNER_TEMP}/benchmark-venv/bin/python" --no-deps dist/*.whl
- name: Collect benchmarks
env:
PYTEST_DISABLE_PLUGIN_AUTOLOAD: "1"
LITELLM_REQUIRE_INSTALLED_WHEEL: "1"
run: >
"${RUNNER_TEMP}/benchmark-venv/bin/python" -I -m pytest
--import-mode=importlib
-p pytest_codspeed.plugin
tests/benchmarks/
--codspeed
--collect-only -q
- name: Run benchmarks
uses: CodSpeedHQ/action@1c8ae4843586d3ba879736b7f6b7b0c990757fab # v4.12.1
with:
mode: simulation
run: >
env PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 LITELLM_REQUIRE_INSTALLED_WHEEL=1
"${RUNNER_TEMP}/benchmark-venv/bin/python" -I -m pytest
--import-mode=importlib
-p pytest_codspeed.plugin
tests/benchmarks/
--codspeed