-
Notifications
You must be signed in to change notification settings - Fork 415
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#9189 In google-ai-edge/LiteRT;
- Status: Open.#9185 In google-ai-edge/LiteRT;
[Tensor SDK Beta] apply_plugin INTERNAL on small TTS graphs while a larger sibling graph compiles (Tensor_G5)
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#9152 In google-ai-edge/LiteRT;- Status: Open.#9045 In google-ai-edge/LiteRT;
- Status: Open.#9023 In google-ai-edge/LiteRT;
Division by a constant zero returns FLT_MAX instead of infinity
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#9021 In google-ai-edge/LiteRT;XNNPACK COS returns values outside [-1, 1] for large float32 inputs
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#9020 In google-ai-edge/LiteRT;GPU delegate misaligns mixed-rank elementwise broadcast inputs
status:awaiting PR reviewawaiting a PR reviewawaiting a PR reviewtype:bugBugBugtype:gpu delegateIssue with GPU delegationIssue with GPU delegationStatus: Open.#8980 In google-ai-edge/LiteRT;- Status: Open.#8979 In google-ai-edge/LiteRT;
Python API : RuntimeError: Failed LiteRtCreateTensorBufferFromHostMemory
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#8946 In google-ai-edge/LiteRT;Technical Update: Systematic Investigation & Failure Localization (apply_plugin / Tensor Backend) -#8062, #8501, and #8884
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#8943 In google-ai-edge/LiteRT;[Bug] no-delegate builtin interpreter corrupts FULLY_CONNECTED output via memory-planner buffer aliasing (XNNPACK/preserve_all_tensors correct)
status:awaiting LiteRTerinformation is sufficient and the issue is escalatedinformation is sufficient and the issue is escalatedtype:bugBugBugStatus: Open.#8928 In google-ai-edge/LiteRT;