Google Git
Sign in
chromium/external/github.com/google-ai-edge/LiteRT-LM/HEAD
  1. 78d5382 feat(cli): group subcommands into Inference, Model Management, and LiteRT-LM File sections in help text by Wai Hon Law · 6 hours ago upstream/main
  2. 609bb73 Enable per-op profiling in LiteRT LM. by Google AI Edge · 6 hours ago
  3. f2f7810 [litertlm] Add SuppressTokensConfig to LiteRT-LM Swift API. by Bangcheng Wang · 6 hours ago
  4. 29b6369 Internal Change Only by Google AI Edge · 9 hours ago
  5. 3568271 Internal change by Google AI Edge · 9 hours ago
  6. 126cc31 Update dependencies of litert_lm by Google AI Edge · 9 hours ago
  7. b48da15 [litertlm] Add NoRepeatNgramConfig to LiteRT-LM Swift API. by Bangcheng Wang · 9 hours ago
  8. e5893b5 Add back proper config for mixed precision of GPU options. by Yi-Chun Kuo · 10 hours ago
  9. 62cfa40 Fix ASAN heap-use-after-free in EmbeddingLookupMultiModal by extending buffer lifetime. by Salil Tambe · 10 hours ago
  10. 12fb7cd [litertlm] Add RepetitionPenaltyConfig and maxOutputTokens to LiteRT-LM Swift API. by Bangcheng Wang · 10 hours ago
  11. 2e38d70 NPU: Report the max sequence length to the Engine to fail more gracefully by Matt Kreileder · 11 hours ago
  12. c72a126 fix(cli): include jsonschema in the PyPI dependency by Wai Hon Law · 11 hours ago
  13. 0e3ee2b Fix zero token and NaN metrics in LiteRT-LM benchmark logging. by Salil Tambe · 15 hours ago
  14. e8afa3b fix(benchmark): pass enable_speculative_decoding in Benchmark.run() by Wai Hon Law · 17 hours ago
  15. ce0fbc3 fix: remove thinking content handling from Qwen3 chat template by Wai Hon Law · 30 hours ago
  16. 372ff7e feat: set filterChannelContentFromKvCache to true by default by Wai Hon Law · 31 hours ago
  17. 7355f6d Add large Gemma 4 models (12B, 26B, 31B) and VRAM warning to LiteRT-LM chat app. by Google AI Edge · 32 hours ago
  18. f35fcbc feat: default filter_channel_content_from_kv_cache to None across CLI and language bindings by Wai Hon Law · 35 hours ago
  19. df23d63 Internal change to enable support for Google Tensor backend by Google AI Edge · 35 hours ago
  20. c74608b Centralize CPU and GPU option configurations across LiteRT-LM executors by Salil Tambe · 35 hours ago
  21. 587d1d6 Add response_format API for constrained decoding (JSON Schema and Regex) in Kotlin. by Wai Hon Law · 2 days ago
  22. e94d740 Internal change by Wai Hon Law · 2 days ago
  23. 0e380a5 On Windows, `ERROR` is defined as a macro. When passed as an argument, the preprocessor expands `ERROR` prematurely, resulting in build breaks. by Google AI Edge · 2 days ago
  24. f947287 Add a flag to set gpu_enable_metal_residency_set by Byungchul Kim · 2 days ago
  25. 5dc3536 [litertlm] Add SuppressTokensConfig to LiteRT-LM Kotlin API. by Bangcheng Wang · 2 days ago
  26. 92f3caa Add support for GPU LoRA weight verification for audio inputs and AST testing. by Salil Tambe · 2 days ago
  27. 2d816fb refactor: extract LiteRT-LM C API internal structs into shared engine_internal.h by Wai Hon Law · 2 days ago
  28. 21a1eba [litertlm] Add NoRepeatNgramConfig to LiteRtLm Kotlin API. by Bangcheng Wang · 2 days ago
  29. 70f8523 Set `self.handle = nil` in `Conversation.deinit` and `Engine.deinit` before native deallocation to prevent re-entry or double-free errors during teardown. by Yishuang Pang · 2 days ago
  30. 36c721f fix: support thinking budget for Qwen models and dynamically select first channel as thinking channel by Wai Hon Law · 2 days ago
  31. 4f2cae6 Reorder constructor initializer list in LlmLiteRtNpuCompiledModelExecutor to match class field declaration order and prevent compiler reordering warnings (-Wreorder-ctor). by Google AI Edge · 2 days ago
  32. 33e0b35 fix: support padded vocabulary sizes in ConstrainedDecoder by Wai Hon Law · 2 days ago
  33. 071264d Support response_format API in LiteRT-LM OpenAI handler. by Wai Hon Law · 2 days ago
  34. e5ab46e NPU execution: Update HW mask for sliding window attention by Matt Kreileder · 2 days ago
  35. 2bedb7b Set NPU backend in CompiledModel options by David Massoud · 2 days ago
  36. d75150e Downgrade most ABSL_LOG(INFO) to ABSL_VLOG. by Google AI Edge · 2 days ago
  37. 9643e94 Internal code update by Tenghui Zhu · 2 days ago
  38. 719ddb4 [litertlm] Add RepetitionPenaltyConfig to LiteRtLm Kotlin API. by Bangcheng Wang · 2 days ago
  39. 3f67cd3 Internal code update by Tenghui Zhu · 2 days ago
  40. c7adc1b Add metadata for LiteRT-LM embedding models. by Matthew Chan · 2 days ago
  41. 4698342 Expose op profiling symbols to litert windows DLL. by Google AI Edge · 2 days ago
  42. 325d683 Add GetTFLiteModelSectionOffsetAndSize to ModelResources. by David Massoud · 2 days ago
  43. 28441e2 Enable residency set configuration. by Fengwu Yao · 3 days ago
  44. d116ee4 Internal changes only. by Fengwu Yao · 3 days ago
  45. 1bdd7da fix: update LiteRtLmConversationConfig test struct layout to match C engine header by Wai Hon Law · 3 days ago
  46. e398f12 NPU: Initial implementation for sliding window attention support in HW cache update by Matt Kreileder · 3 days ago
  47. fddcd26 Add residency API setting. by Fengwu Yao · 3 days ago
  48. 4771083 Fix Windows model download path resolution in api_test.py using shutil.which. by Google AI Edge · 3 days ago
  49. 2a51e94 fix(cli): allow additional properties in config.json schema by Wai Hon Law · 3 days ago
  50. 5b92c80 Rename verify_api.py to api_test.py, configure GCS model downloads, fix Kokoro apt lock timeouts. by Google AI Edge · 3 days ago
  51. ef16b76 This is an internal change by Google AI Edge · 3 days ago
  52. 5ae2b32 Internal change by Google AI Edge · 3 days ago
  53. ef12fc2 feat(python): add response format API by Wai Hon Law · 3 days ago
  54. 13df7ab This is an internal change by Google AI Edge · 3 days ago
  55. 98eba9b Skip macOS gated model download and pytest on unauthenticated pull requests. by Salil Tambe · 3 days ago
  56. 2a568b8 feat(cli): add --chat-template option to litert-lm run by Wai Hon Law · 3 days ago
  57. 3852882 Implement single-turn prompt template rendering for GenericDataProcessor by delegating to RenderSingleTurnTemplateCommon. Also add unit tests verifying RenderSingleTurnTemplate for single-turn rendering and appending message flows. by Google AI Edge · 3 days ago
  58. 4991db6 feat(cli): add 9 new config options to config.json and validate via JSON Schema by Wai Hon Law · 3 days ago
  59. bea5562 [litertlm] Add SuppressTokensConfig to LiteRT LM C API and Python bindings. by Bangcheng Wang · 3 days ago
  60. 6340ece Fix Hugging Face S3 redirect 403 authorization failures on macOS and Linux CI workflows by Salil Tambe · 3 days ago
  61. 8cafae3 Update GetOptimizedPrefillWorkGroups to use cautious greedy algorithm by Marissa Ikonomidis · 4 days ago
  62. f871d8d [litertlm] Add NoRepeatNgramConfig to LiteRT LM C and Python APIs. by Bangcheng Wang · 4 days ago
  63. 4790839 Prepare only 1 step ahead of command buffer for single KV cache case by Byungchul Kim · 4 days ago
  64. 5c17868 Optimize MTP rejection sampling verifier batch locking by Salil Tambe · 4 days ago
  65. e5f9ba7 feat(cli): add pack and unpack commands and litertlm_builder.pack API by Wai Hon Law · 4 days ago
  66. 69cb398 feat(cli): add --speculative-decoding option and deprecate --enable-speculative-decoding; update --thinking options by Wai Hon Law · 4 days ago
  67. 44d2a22 Update CI build to download model from GCS instead of Hugging Face. by Google AI Edge · 4 days ago
  68. da33e30 feat(cli): support configuration via config.json and validation via JSON Schema by Wai Hon Law · 5 days ago
  69. db900bd Reset current context and executor if only session is released by Byungchul Kim · 5 days ago
  70. 020a3c0 Guard HuggingFaceTokenizer include with a build flag by Google AI Edge · 5 days ago
  71. 83a91b5 Update dependencies of litert_lm by Byungchul Kim · 6 days ago
  72. 156e8d8 feat(cli): use blue for all channel contents and print [/channel-name] at channel end by Wai Hon Law · 7 days ago
  73. 840fe9e Correct wrong condition to enable sampler handling input by Byungchul Kim · 7 days ago
  74. 056d1ba Internal changes only by Bangcheng Wang · 7 days ago
  75. 1d3024f Update checksums for LiteRT-LM v0.14.0 binary targets. by Google AI Edge · 8 days ago
  76. ad53ed1 Allow configurable NPU KV cache initialization value via model metadata. by Andrew Zhang · 8 days ago upstream/v0.15.0-alpha0
  77. 36af951 ci: add -c opt and unify bazel disk and repository cache paths in macOS CI workflow by Wai Hon Law · 8 days ago
  78. 5c1cd36 [litertlm] Add RepetitionPenaltyConfig to LiteRT LM C and Python APIs. by Bangcheng Wang · 8 days ago
  79. 60c408e style(cli): format non-streaming OpenAI handler JSON responses with 2-space indentation and trailing newline by Wai Hon Law · 8 days ago
  80. 105dcba Support varying audio chunk size for streaming audio encoder models by Yi-Chun Kuo · 8 days ago
  81. b0ac2f9 Reverts df914b949e728bced8059506d45736024720a51c by Fengwu Yao · 9 days ago
  82. 4c48743 Create test_lm_multi_prefill.litertlm for testing multi-prefill. by Matthew Chan · 9 days ago
  83. 8a4a12b Support varying audio chunk size for streaming audio encoder models by Google AI Edge · 9 days ago
  84. 862d3c0 feat(cli): add reasoning_tokens to usage in OpenAI chat completions endpoint by Wai Hon Law · 9 days ago
  85. eeb4802 Enable LFM on-device testing for Exynos NPU by Salil Tambe · 9 days ago
  86. ba9a470 feat(swift): expose ThinkingConfig and thinking token budget in Swift API by Wai Hon Law · 9 days ago
  87. df914b9 Update dependencies of litert_lm by Fengwu Yao · 9 days ago
  88. ca4dadc Automated Code Change by Google AI Edge · 9 days ago
  89. c8bc396 Support varying audio chunk size for streaming audio encoder models by Yi-Chun Kuo · 9 days ago
  90. 5dd1326 Fix premature callback invocation and empty prefill hang in Conversation. by Google AI Edge · 9 days ago
  91. 910fb26 [litertlm] Support completion_usage object in OpenAI server handler by Wai Hon Law · 9 days ago
  92. e62cbd2 feat(cli): support reasoning_effort parameter in OpenAI server handler by Wai Hon Law · 9 days ago
  93. 4174318 Bump version to 0.15.0 by Google AI Edge · 9 days ago
  94. fa7268c Fix msan failure by initializing memory of audio buffer in cached_session_test. by Matthew Chan · 9 days ago
  95. c27a4a8 Add LaTeX rendering to LiteRT-LM web chat app by Google AI Edge · 9 days ago
  96. 5893966 feat(kotlin): expose ThinkingConfig and thinking token budget in Kotlin API by Wai Hon Law · 9 days ago
  97. 2e4796b feat(cli): group thinking related options under the --thinking prefix by Wai Hon Law · 10 days ago
  98. d2b8a38 feat(kotlin): add maxOutputToken API to ConversationConfig and sendMessage by Wai Hon Law · 10 days ago
  99. dd411af fix(python): provide distinct error messages for different NPU initialization failures by Wai Hon Law · 10 days ago
  100. 440c37a ci: add --repository_cache flag and paths across Linux, Android, and macOS workflows by Wai Hon Law · 10 days ago