0.5.3

What's Changed

• 🐛 handle MistralTokenizer special case by @prashantgupta24 in #162

Full Changelog: 0.5.2...0.5.3

0.5.2

What's Changed

• gha: fix caching strategy by @dtrifiro in #154
• build(deps): bump prometheus-client from 0.20.0 to 0.21.0 by @dependabot in #151
• build(deps): bump types-protobuf from 5.27.0.20240907 to 5.28.0.20240924 by @dependabot in #150
• ✨ add pt_to_prompt cli by @prashantgupta24 in #155
• Exploit vLLM options to return deltas/final-output only by @njhill in #137
• build(deps): bump ruff from 0.6.7 to 0.6.9 by @dependabot in #157
• Fix bug in example. by @tdoublep in #159
• pre-commit autoupdate by @github-actions in #142
• fix linter complaints, cleanup gha caching by @dtrifiro in #160
• gha: add ccache by @dtrifiro in #147
• build(deps): bump grpcio from 1.62.2 to 1.66.2 by @dependabot in #153
• Fail startup with root-cause exception by @njhill in #156
• ✨ invoke caikit -> peft conversion at load time by @joerunde in #161

New Contributors

• @tdoublep made their first contribution in #159

Full Changelog: 0.5.1...0.5.2

0.5.1

What's Changed

• gha: implement caching by @dtrifiro in #145
• 🐛 don't use vllm.commit by @prashantgupta24 in #148
• fix: add_special_tokens in tokenize by @rafvasq in #144

Full Changelog: 0.5.0...0.5.1

0.5.0

What's Changed

• pre-commit autoupdate by @github-actions in #104
• build(deps): bump ruff from 0.6.1 to 0.6.3 by @dependabot in #116
• gha: use vllm v0.6.1 for testing by @dtrifiro in #125
• Add OWNER file by @vaibhavjainwiz in #124
• build(deps): bump mypy from 1.11.1 to 1.11.2 by @dependabot in #107
• build(deps): bump accelerate from 0.33.0 to 0.34.2 by @dependabot in #123
• build(deps): bump types-protobuf from 5.26.0.20240422 to 5.27.0.20240907 by @dependabot in #120
• build(deps): update opentelemetry-api requirement from <1.27.0,>=1.26.0 to >=1.26.0,<1.28.0 by @dependabot in #122
• pre-commit autoupdate by @github-actions in #119
• do not run codecov upload step on dependabot PR by @NickLucche in #129
• Write to /dev/termination-log on main loop exception by @NickLucche in #118
• http_server: compatibility fixes for vllm>0.6.1.post1 by @dtrifiro in #136
• Propagate cancellation of gRPC requests by @njhill in #130
• pre-commit autoupdate by @github-actions in #127
• Fix calls to defunct AsyncEngineClient by @NickLucche in #138
• 🐛 fix nargs + or * by @joerunde in #140
• build(deps): bump pytest from 8.3.2 to 8.3.3 by @dependabot in #131
• build(deps): update opentelemetry-sdk requirement from <1.27.0,>=1.26.0 to >=1.26.0,<1.28.0 by @dependabot in #133
• build(deps): bump ruff from 0.6.3 to 0.6.7 by @dependabot in #139
• grpc_server: use x-correlation-id as request-id when possible by @dtrifiro in #128
• build(deps): bump types-requests from 2.32.0.20240712 to 2.32.0.20240914 by @dependabot in #132
• build(deps): update opentelemetry-exporter-otlp requirement from <1.27.0,>=1.26.0 to >=1.26.0,<1.28.0 by @dependabot in #135
• deps: bump vllm minimum version to 0.6.2 by @dtrifiro in #143

New Contributors

• @github-actions made their first contribution in #104
• @vaibhavjainwiz made their first contribution in #124
• @NickLucche made their first contribution in #129

Full Changelog: 0.4.1...0.4.2

0.4.1

What's Changed

• build(deps): bump ruff from 0.5.5 to 0.6.1 by @dependabot in #100
• build(deps): bump accelerate from 0.32.1 to 0.33.0 by @dependabot in #93
• fix gha pre commit autoupdate by @dtrifiro in #103
• pyproject: Pin OpenTelemetry versions by @ronensc in #106
• fix: handle negative token rank when logprobs disabled by @tjohnson31415 in #105
• ✨ add x-correlation-id in gRPC metadata by @prashantgupta24 in #113
• ♻️ updates for vLLM==0.5.5 by @prashantgupta24 in #112

Full Changelog: 0.4.0...0.4.1

0.4.0

What's Changed

• fix: consistent env var parsing for all boolean args in vLLM by @tjohnson31415 in #98
• 🐛 fix input text issue by @prashantgupta24 in #97

Full Changelog: 0.3.0...0.4.0

0.3.0

What's new

• Add model-util CLI by @rafvasq in #59:

  Adds commands to the adapter using either entry point model-util or text-generation-server
  - model-util download-weights
  - model-util convert-to-safetensors
  - model-util convert-to-fast-tokenizer

• add --disable-prompt-logprobs argument by @tjohnson31415 in #95

What's Changed

• Revert "fix merge_async_iterators usage for vLLM>0.5.4" by @dtrifiro in #88
• fix parsing of env vars by @dtrifiro in #94
• gha: add pre-commit autoupdate workflow by @dtrifiro in #89
• fix: correct parsing of command line bool arg values by @tjohnson31415 in #96

New Contributors

• @tjohnson31415 made their first contribution in #95
• @rafvasq made their first contribution in #59

Full Changelog: 0.2.4...0.3.0

0.2.4

Highlights

• Compatibility with vLLM v0.5.4
• Bump minimum vLLM requirement to v0.5.4

What's Changed

• remove dead code (vllm<=0.5.0.post1) by @dtrifiro in #65
• build(deps): bump ruff from 0.5.4 to 0.5.5 by @dependabot in #72
• pyproject: fix broken URLs by @dtrifiro in #76
• gha: add missing build dependencies by @dtrifiro in #68
• noxfile: make overridden vllm version install verbose by @dtrifiro in #78
• updates for vLLM==0.5.4 by @dtrifiro in #82
• fix merge_async_iterators usage for vLLM>0.5.4 by @dtrifiro in #86
• build(deps): bump hf-transfer from 0.1.6 to 0.1.8 by @dependabot in #73
• build(deps): bump flash-attn from 2.6.1 to 2.6.3 by @dependabot in #71
• pre-commit: bump deps by @dtrifiro in #67
• Extract request's trace context in GenerateStream() by @ronensc in #64
• Make ADD_SPECIAL_TOKENS true by default by @maxdebayser in #66
• build(deps): bump pytest from 8.2.2 to 8.3.2 by @dependabot in #70
• Fix stop_reason for secondary eos tokens by @njhill in #75
• ♻️ refactor LoRARequest based on upstream by @prashantgupta24 in #74
• build(deps): bump mypy from 1.10.1 to 1.11.1 by @dependabot in #77
• Fix length penalty logit processor getting NaN by @wallashss in #85
• Re-enable seed for pipeline parallel by @njhill in #69
• 🥅 Kill servers on engine death by @joerunde in #63

New Contributors

• @ronensc made their first contribution in #64
• @maxdebayser made their first contribution in #66
• @wallashss made their first contribution in #85

Full Changelog: 0.2.3...0.2.4

0.2.3

What's Changed

• build(deps): bump accelerate from 0.31.0 to 0.32.1 by @dependabot in #42
• build(deps): bump flash-attn from 2.5.9.post1 to 2.6.1 by @dependabot in #45
• Fix earlier LoRA tokenizer changes by @njhill in #53
• build(deps): bump ruff from 0.5.1 to 0.5.2 by @dependabot in #43
• build(deps): bump types-requests from 2.32.0.20240602 to 2.32.0.20240712 by @dependabot in #44
• Fix tokenize endpoint by @njhill in #54
• build(deps): bump ruff from 0.5.2 to 0.5.4 by @dependabot in #58
• vLLM 5.3+ support by @joerunde in #60

New Contributors

• @joerunde made their first contribution in #60

Full Changelog: 0.2.2...0.2.3

0.2.2

Full Changelog: 0.2.1...0.2.2

What's Changed

• tests: fix lora tests handling by @dtrifiro in #51
• fix missing metrics endpoint by @dtrifiro in #50

Full Changelog: 0.2.1...0.2.2