v0.1.5
What's Changed
- feat: add further metrics around requests and token gen times by @maschad in #346
- feat: add prometheus metrics for each possible docker compose profiles by @jorgeantonio21 in #349
- feat: handle lints and refactor intra token timer to inter token timer by @jorgeantonio21 in #350
- ci: update ci job to catch lint errors by @maschad in #351
- docs: update
README
with further instructions for setup by @maschad in #353 - docs: update setup script link by @maschad in #354
- feat: add support for multiple chat completions services by @jorgeantonio21 in #355
- ci: add dependabot by @maschad in #356
- ci: add cargo audit to ci by @maschad in #360
- chore(deps): bump docker/build-push-action from 5 to 6 by @dependabot in #361
- chore(deps): bump thiserror from 1.0.69 to 2.0.11 by @dependabot in #367
- chore(deps): bump http from 0.2.12 to 1.2.0 by @dependabot in #363
- ci: add some dependencies to be ignored by @maschad in #368
- chore(deps): bump rustsec/audit-check from 1 to 2 by @dependabot in #371
- ci: integrated coverage by @maschad in #357
- build: fix issue related to rustls audit by @maschad in #369
- feat: update sui testnet versions and tdx by @jorgeantonio21 in #372
- ci: add e2e test job by @maschad in #366
- chore: update vllm by @francis2tm in #373
- feat: update docker compose test yaml by @jorgeantonio21 in #375
- chore: use stricter linting for builds by @maschad in #358
- ci: cargo deny on push/pull requests by @maschad in #370
- feat: remove the usage removal from the streaming chunk signing by @jorgeantonio21 in #376
- feat: update return of appropriate status code from inference service by @jorgeantonio21 in #377
- feat: deprecate the use of max_tokens to max_completion_tokens, following openai api spec by @jorgeantonio21 in #378
- ci: add workflow dispatch for e2e tests by @maschad in #381
- chore: add pre-commit hooks for
clippy
by @maschad in #382 - feat: resolve issue with hooks doc and grafana incorrect port by @jorgeantonio21 in #383
- feat: update vllm docker image version by @jorgeantonio21 in #384
- ci: update audit permissions +
openssl
dep by @maschad in #389 - chore(deps): bump tempfile from 3.15.0 to 3.16.0 by @dependabot in #385
- chore(deps): bump hyper from 1.5.2 to 1.6.0 by @dependabot in #386
- chore(deps): bump serde_json from 1.0.137 to 1.0.138 by @dependabot in #387
- chore(deps): bump codecov/codecov-action from 4 to 5 by @dependabot in #388
New Contributors
- @maschad made their first contribution in #346
- @dependabot made their first contribution in #361
Full Changelog: v0.1.4...v0.1.5