issues
search
alibaba
/
TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
MIT License
760
stars
116
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to quantize ViT model with quantization aware training
#374
Linsop2
opened
4 weeks ago
3
How to remove the Quantize and Dequantize layer on tflite
#373
Linsop2
closed
1 month ago
2
出现TypeError: issubclass() arg 2 must be a class, a tuple of classes, or a union
#372
xianzhixiong
closed
1 month ago
2
[misc] update Python & PyTorch constraint
#371
peterjc123
closed
1 month ago
0
support weight int16 convert and fake quant
#370
zk1998
opened
1 month ago
0
[tracer] apply move_idx=True for graph.insert_between
#369
peterjc123
closed
1 month ago
0
Custom softmax fails to convert
#368
spacycoder
closed
1 month ago
1
[quantizer] add linear support for CLE
#367
zk1998
closed
1 month ago
0
[converter] fix converter sym_zp check
#366
zk1998
closed
1 month ago
0
[tracer] skip unsupport torchvision op
#365
zk1998
closed
1 month ago
0
Mul + Add quantization
#364
spacycoder
closed
1 month ago
8
[converter] set hybrid_q_type for int16
#363
peterjc123
closed
1 month ago
0
[converter] skip hybrid_quantize_weight_type check for non hybrid qua…
#362
peterjc123
closed
1 month ago
0
BatchMatMul quantization
#361
spacycoder
closed
2 months ago
2
[converter] same q_params for neg in mul_scalar
#360
peterjc123
opened
2 months ago
0
Model with stack does not work with int8 target type
#359
spacycoder
opened
2 months ago
15
[docs] fix docs for ONNX2Torch
#358
peterjc123
closed
2 months ago
0
[tracer] fix FUNCTIONAL_MODULE_MAPPING
#357
peterjc123
closed
2 months ago
0
[tracer] Add config for PyTorch2.4
#356
zk1998
closed
2 months ago
0
RMS Norm doesn't seem to be supported
#355
spacycoder
opened
2 months ago
5
Model with "concatenate" layer does not export correctly with int8
#354
spacycoder
closed
2 months ago
2
Converting model with "per_tensor = False" does not work
#353
spacycoder
closed
2 months ago
1
[converter] add fuse_gather_conv2d_pass
#352
peterjc123
closed
3 months ago
0
[converter] add fuse_simple_gather_pass
#351
peterjc123
closed
3 months ago
0
[quantizer] fix clamp_with_fusion
#350
peterjc123
closed
3 months ago
0
[converter] fix np.pow for hybrid_quantizer
#349
peterjc123
closed
3 months ago
0
[converter] fix unhashable keys for group_tensors_pass
#348
peterjc123
closed
3 months ago
0
[examples] add bidirectional LSTMs
#347
peterjc123
closed
3 months ago
0
[converter] correct non-compliant axis handling in split and splitV ops
#346
LynnL4
closed
3 months ago
6
QAT problem on YOLOv9
#345
hoangtv2000
closed
4 months ago
8
[examples] fix vit ptq
#344
peterjc123
closed
4 months ago
0
ViT PTQ Error
#343
hoangtv2000
closed
4 months ago
2
[doc] qconfig layerwise modify
#342
zk1998
closed
4 months ago
0
[converter] use abs max for int16 lstm cell state quantization params
#341
peterjc123
closed
4 months ago
0
[tracer&quantizer&converter] int16 cell state qparams
#340
peterjc123
closed
4 months ago
0
[quantizer] add lstm weight fake_quant to align tflite
#339
zk1998
closed
4 months ago
0
[quantizer] set int16 scale for cell act
#338
peterjc123
closed
4 months ago
0
Huge loss when applying QAT on YOLOv8n
#337
hoangtv2000
closed
4 months ago
40
[converter] add intermediate tensors for Int16 LSTM
#336
peterjc123
closed
5 months ago
0
[converter] int16 dynamic quantized lstm
#335
peterjc123
closed
5 months ago
0
[quantizer] add quantize_op_action config to disable op quantization
#334
zk1998
closed
5 months ago
0
[CI] fix mac13 fulltest error
#333
zk1998
closed
5 months ago
0
[CI] fix refined ci runner
#332
zk1998
closed
5 months ago
0
[converter] fix tensor check constraint
#331
peterjc123
closed
5 months ago
0
关于模型中使用了nn.Parameter()会导致转TFlite会失败的问题
#330
Bun-TianYi
closed
5 months ago
5
[converter] remove_tile_before_binary_elementwise_ops
#329
peterjc123
closed
5 months ago
0
[CI] refined ci runner
#328
zk1998
closed
5 months ago
0
[CI] fix windows CI for PT 1.8/1.9
#327
peterjc123
closed
5 months ago
0
[pruner] fix transformer pruner error
#326
zk1998
closed
5 months ago
0
OneShot Pruning Tensor Size Mismatch Error
#325
zeo233
closed
5 months ago
4
Next