Google Git
Sign in
chromium/external/github.com/google-ai-edge/LiteRT-LM/HEAD
  1. 156e8d8 feat(cli): use blue for all channel contents and print [/channel-name] at channel end by Wai Hon Law · 2 days ago upstream/main
  2. 840fe9e Correct wrong condition to enable sampler handling input by Byungchul Kim · 2 days ago
  3. 056d1ba Internal changes only by Bangcheng Wang · 2 days ago
  4. 1d3024f Update checksums for LiteRT-LM v0.14.0 binary targets. by Google AI Edge · 2 days ago
  5. ad53ed1 Allow configurable NPU KV cache initialization value via model metadata. by Andrew Zhang · 3 days ago
  6. 36af951 ci: add -c opt and unify bazel disk and repository cache paths in macOS CI workflow by Wai Hon Law · 3 days ago
  7. 5c1cd36 [litertlm] Add RepetitionPenaltyConfig to LiteRT LM C and Python APIs. by Bangcheng Wang · 3 days ago
  8. 60c408e style(cli): format non-streaming OpenAI handler JSON responses with 2-space indentation and trailing newline by Wai Hon Law · 3 days ago
  9. 105dcba Support varying audio chunk size for streaming audio encoder models by Yi-Chun Kuo · 3 days ago
  10. b0ac2f9 Reverts df914b949e728bced8059506d45736024720a51c by Fengwu Yao · 3 days ago
  11. 4c48743 Create test_lm_multi_prefill.litertlm for testing multi-prefill. by Matthew Chan · 3 days ago
  12. 8a4a12b Support varying audio chunk size for streaming audio encoder models by Google AI Edge · 3 days ago
  13. 862d3c0 feat(cli): add reasoning_tokens to usage in OpenAI chat completions endpoint by Wai Hon Law · 3 days ago
  14. eeb4802 Enable LFM on-device testing for Exynos NPU by Salil Tambe · 4 days ago
  15. ba9a470 feat(swift): expose ThinkingConfig and thinking token budget in Swift API by Wai Hon Law · 4 days ago
  16. df914b9 Update dependencies of litert_lm by Fengwu Yao · 4 days ago
  17. ca4dadc Automated Code Change by Google AI Edge · 4 days ago
  18. c8bc396 Support varying audio chunk size for streaming audio encoder models by Yi-Chun Kuo · 4 days ago
  19. 5dd1326 Fix premature callback invocation and empty prefill hang in Conversation. by Google AI Edge · 4 days ago
  20. 910fb26 [litertlm] Support completion_usage object in OpenAI server handler by Wai Hon Law · 4 days ago
  21. e62cbd2 feat(cli): support reasoning_effort parameter in OpenAI server handler by Wai Hon Law · 4 days ago
  22. 4174318 Bump version to 0.15.0 by Google AI Edge · 4 days ago
  23. fa7268c Fix msan failure by initializing memory of audio buffer in cached_session_test. by Matthew Chan · 4 days ago
  24. c27a4a8 Add LaTeX rendering to LiteRT-LM web chat app by Google AI Edge · 4 days ago
  25. 5893966 feat(kotlin): expose ThinkingConfig and thinking token budget in Kotlin API by Wai Hon Law · 4 days ago
  26. 2e4796b feat(cli): group thinking related options under the --thinking prefix by Wai Hon Law · 4 days ago
  27. d2b8a38 feat(kotlin): add maxOutputToken API to ConversationConfig and sendMessage by Wai Hon Law · 4 days ago
  28. dd411af fix(python): provide distinct error messages for different NPU initialization failures by Wai Hon Law · 4 days ago
  29. 440c37a ci: add --repository_cache flag and paths across Linux, Android, and macOS workflows by Wai Hon Law · 4 days ago
  30. 305324b ci(win): optimize execution time of Windows ML-CI workflow by ~47% by Wai Hon Law · 4 days ago
  31. 7ba7ac9 LiteRT-LM NPU: Support models with sliding window attention by Matt Kreileder · 4 days ago
  32. a8eb6fd [litertlm] Add --no_repeat_ngram_size` and `--no_repeat_ngram_window_size flags to LiteRT LM. by Bangcheng Wang · 5 days ago
  33. 089d44e [litertlm] Integrate NoRepeatNgramConfig into the decoding pipeline. by Bangcheng Wang · 5 days ago
  34. c2ab9ab feat(python): add C and Python APIs for thinking token budget and ThinkingConfig by Wai Hon Law · 5 days ago
  35. aece6ae [litertlm] Refactor RepetitionPenaltyConfig and SuppressTokensConfig handling. by Bangcheng Wang · 5 days ago
  36. 3c0d244 Add Web Demo link to README. by Google AI Edge · 5 days ago
  37. cc6660e Use filesystem API for local models in Web demo (if available) by Google AI Edge · 5 days ago
  38. 2fd31fb Add option to upload your own model to litertlm web chat demo by Google AI Edge · 5 days ago
  39. aaf44be Lazy-load `per_layer_embedding_lookup_manager_` in NPU executor by Salil Tambe · 5 days ago
  40. 0d4272f refactor: use strongly typed C enums for log severity and activation data type by Wai Hon Law · 5 days ago
  41. eaccbaf Expose session and conversation cloning to the LiteRT-LM JS API. by Google AI Edge · 5 days ago
  42. cf6b506 Ensure LiteRT-LM builder and CLI reject writes to CNS paths by Google AI Edge · 5 days ago
  43. 6ee714b Update LiteRT-LM binary targets to v0.14.0. by Google AI Edge · 5 days ago
  44. cd1131d Re-enable pytest in CI workflows. by Google AI Edge · 5 days ago
  45. 76cda1d update to absl native status macros by Mohammadreza Heydary · 5 days ago
  46. 73b5ab9 Reverts d2e3ba197774ef1cc06790f5e913cc3b79b0a48f by Tenghui Zhu · 5 days ago
  47. 5112706 feat: group thinking settings into ThinkingConfig and fix preface override by Wai Hon Law · 6 days ago
  48. 5b1a65c Internal changes only by Byungchul Kim · 6 days ago
  49. d2e3ba1 Update dependencies of litert_lm by Byungchul Kim · 6 days ago
  50. 0cef57d Internal code update by Tenghui Zhu · 6 days ago
  51. 40a06e3 Expose prefillPrefaceOnInit in Kotlin API. by Matthew Chan · 6 days ago
  52. 4912f2d Implement CachedSession and PrefixCache for stateful prefix caching. by Matthew Chan · 6 days ago
  53. f83632c [litertlm] Add support for suppress tokens in LlmMetadata. by Bangcheng Wang · 6 days ago
  54. 790e356 Gracefully fallback from file backed model loading on unsupported platforms by Google AI Edge · 8 days ago
  55. c948964 refactor(c): refactor streaming callback to use opaque LiteRtLmStreamChunk for ABI stability by Wai Hon Law · 9 days ago
  56. b516ae3 Add implementation that uses embeddings for NPU based inference. by Salil Tambe · 10 days ago
  57. dea59ae Internal code update by Tenghui Zhu · 10 days ago
  58. cb10159 Add unpack feature to LiteRT-LM builder Python API and CLI by Google AI Edge · 11 days ago
  59. ade3eeb Internal change by Google AI Edge · 11 days ago
  60. 79fcae7 Add --repetition_penalty, --presence_penalty, --frequency_penalty, --repetition_window_size flag to LiteRT LM. by Google AI Edge · 11 days ago
  61. 471b06d Add --suppress_tokens flag to LiteRT LM. by Google AI Edge · 12 days ago
  62. deb62d2 Support JPEG and PNG decoding for SkiaImagePreprocessor. by Google AI Edge · 12 days ago
  63. 7abc603 [litertlm] Integrate SuppressTokensConfig into the decoding pipeline. by Google AI Edge · 12 days ago
  64. eb13ddd Internal change by Google AI Edge · 12 days ago
  65. 1f8e234 Increase tee stream ring buffer size from 2MB to 20MB by Google AI Edge · 12 days ago
  66. fc17d11 [litertlm] Add SuppressTokensProcessor to ban suppress tokens during decoding by Google AI Edge · 12 days ago
  67. 4283989 [litertlm] Add NoRepeatNgramProcessor to ban repeated n-grams during decoding by Google AI Edge · 13 days ago
  68. 46c5fe0 Update dependencies of litert_lm by Tenghui Zhu · 13 days ago
  69. 645fcac Fix token ids used for HW PLE Lookup by Google AI Edge · 14 days ago
  70. a3c76d2 Update dependencies of litert_lm by Tenghui Zhu · 14 days ago
  71. 23f36e8 tensor api litert-lm executor by Ping Yu · 2 weeks ago
  72. 7d83107 Fix windows build error with the latest absl by Byungchul Kim · 2 weeks ago
  73. 351a8e7 Fix LiteRT NPU quality regression in mask update CPU fallback. by Andrew Zhang · 2 weeks ago
  74. c84063a Make Python API's default sampler param match the engine's default value by Google AI Edge · 2 weeks ago
  75. e8ec426 Update dependencies of litert_lm by Byungchul Kim · 2 weeks ago
  76. daa8ea8 Remove litert_link_capi_so as it's deprecated by Byungchul Kim · 2 weeks ago
  77. 540c56a Add utility to convert Hugging Face LoRA safetensors to LiteRT TFLite format. by Salil Tambe · 2 weeks ago
  78. b5b7b78 feat: support channel output like "thinking" in run_litert_lm.sh by Wai Hon Law · 2 weeks ago
  79. 49ff7de Add js tool use to litert-lm web chat demo by Google AI Edge · 2 weeks ago
  80. ea15123 refactor(c): make LiteRtLmSamplerParams opaque for ABI stability by Wai Hon Law · 2 weeks ago
  81. 5d8ae5f Deprecate Generate API from Session by Salil Tambe · 2 weeks ago
  82. ad60aee refactor(c): make LiteRtLmInputData opaque for ABI stability by Wai Hon Law · 2 weeks ago
  83. d2bdbe2 chore(cli): clean up the comma-separated model id in openai_handler.py by Wai Hon Law · 2 weeks ago
  84. 8715a62 Make vision adapter optional in LiteRt LM vision executor. by Yi-Chun Kuo · 2 weeks ago
  85. dad63c5 internal library cleanup by Yi-Chun Kuo · 2 weeks ago
  86. 63dfea4 ci(cli): include the litert-lm CLI in MacOS CI by Wai Hon Law · 2 weeks ago
  87. 1a775b7 Support optional valid mask in NPU executor. by Andrew Zhang · 3 weeks ago
  88. c1c0a55 chore(cli): clean up the comman-separated model id in gemini handler.py by Wai Hon Law · 3 weeks ago
  89. 10fa4b4 Internal change by Google AI Edge · 3 weeks ago
  90. 27106e3 Add support for multi-modal inputs for liter-lm cli by Google AI Edge · 3 weeks ago
  91. 1af461d Use preprocessors and tokenizers in LiteRT support by Byungchul Kim · 3 weeks ago
  92. df9bb05 Internal change by Google AI Edge · 3 weeks ago
  93. 45d07ac feat(cli): support auto backend for audio and vision by Wai Hon Law · 3 weeks ago
  94. 1cd5d48 Add comprehensive standalone Python wheel verification suite by Google AI Edge · 3 weeks ago
  95. 57b6219 Add tool calling to LiteRT-LM.js by Google AI Edge · 3 weeks ago
  96. d5316d6 Add "--activation-data-type" to cli by Terry Heo · 3 weeks ago
  97. fb9135e Reverts 1fa764e6621ca9a8471e8e0f761ad3853ef13f62 by Terry Heo · 3 weeks ago
  98. 2effc4b Migrate GitHub Actions caching to Google Cloud Storage. by Google AI Edge · 3 weeks ago
  99. 0a65909 Fixed the GPU cache file handling issue. by Google AI Edge · 3 weeks ago
  100. 1fa764e Allow to override force_f32 setting via environment variable by Terry Heo · 3 weeks ago