Skip to content

Actions: google-ai-edge/litert-torch

Actions

auto-assignment

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assignment.yml
94 workflow runs
94 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Failed to prepare model for QAT in Pt2e auto-assignment #95: Issue #801 opened by jimmy133719
8s
8s
I have a model that has two different inputs, can I quantize it so that each input will have different bias and scale? auto-assignment #94: Issue #800 opened by orena1
9s
9s
Compatibility with tensorboard 2.20.0 auto-assignment #93: Issue #794 opened by Pedro2um
7s
7s
Convert google/medgemma-4b-it to TFLite (or provide guidance) auto-assignment #92: Issue #783 opened by william-lijunxuan
7s
7s
wrong conversion for input shapes auto-assignment #91: Issue #780 opened by zyb8543d
10s
10s
GGxAi auto-assignment #90: Issue #758 opened by GGxAi10
9s
9s
GgxAi auto-assignment #89: Issue #757 opened by GGxAi10
9s
9s
How to convert a fine-tuned Gemma-3n model to .task format for AI Edge Gallery? auto-assignment #88: Issue #754 opened by ericrisco
8s
8s
Gemma3n example auto-assignment #87: Issue #753 opened by bil-ash
13s
13s
Basic example not working auto-assignment #86: Issue #752 opened by knelson-hme
9s
9s
How to convert Gemma-3n to .task model auto-assignment #85: Issue #750 opened by mekpro
9s
9s
torch.mean != tfl.mean auto-assignment #84: Issue #743 opened by maxstrobel
21s
21s
Build Issue with text_generation_main auto-assignment #83: Issue #736 opened by Hardik-Choraria
8s
8s
Questions about text_generator_main.cc auto-assignment #82: Issue #735 opened by liamsun2019
9s
9s
Convert with a subset of TFLite built-in OPs auto-assignment #81: Issue #734 opened by hayhan
11s
11s
Disabling use_dus doesn’t prevent generation of StableHLO scatter node auto-assignment #80: Issue #733 opened by Hardik-Choraria
11s
11s
Please provide support for a gemma3-4b model in the examples auto-assignment #79: Issue #730 opened by or1324
12s
12s
KV cached LLMs, like fp32 & fp16 quant, consume too much physical memory auto-assignment #78: Issue #729 opened by hayhan
11s
11s
How to resolve same-scale constraint violation during quantization? auto-assignment #77: Issue #728 opened by erwinbonsmatopic
12s
12s
Option to Disable kv_cache for Generative Models in ai_edge_torch auto-assignment #76: Issue #723 opened by Hardik-Choraria
10s
10s
Extremely disappointed with this project auto-assignment #75: Issue #721 opened by svobora
11s
11s
nn.LayerNorm produces correct output on CPU but wrong output on GPU in exported TFLite models (AI Edge Torch ≥ 0.4.0) auto-assignment #74: Issue #718 opened by kadu-v
9s
9s
FullyConnected + ReLU fusion broken in AI Edge Torch ≥ 0.4.0 (bias broadcasting prevents GPU execution) auto-assignment #73: Issue #717 opened by kadu-v
10s
10s
dynamic shapes in Conv1D and ReLu auto-assignment #72: Issue #716 opened by wangjuan313
9s
9s
Attempting to broadcast a dimension of length 20480 at -1 auto-assignment #71: Issue #715 opened by mrlzla
9s
9s