Conversation
qcdipankar
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
| requires-python = ">=3.8,<3.11" | ||
| dependencies = [ | ||
| "transformers==4.55.0", | ||
| "transformers==4.57.0", |
There was a problem hiding this comment.
@quic-rishinr / @quic-hemagnih : can we trigger TA?
There was a problem hiding this comment.
Yes we should raise it, and start the run of all the models with 4.57 in parallel, typically it takes 1week.
| attention_mask, torch.tensor(MIN_MASKED_ATTENTION_VALUE, dtype=torch.float32), attn_weights | ||
| ) | ||
|
|
||
| attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype) |
There was a problem hiding this comment.
can you set this to dtype passed from pretrained()
quic-hemagnih
left a comment
quic-hemagnih
left a comment
There was a problem hiding this comment.
I am still reviewing the modelling file.
examples/qwen3_vl/qwen3_vl.py
Outdated
|
|
||
| messages = [messages] * batch_size | ||
|
|
||
| inputs = processor.apply_chat_template( |
There was a problem hiding this comment.
I think we can combine the code from line 62 to 77 and 122 to 140 at one place.
Idea is to avoid the code repetition.
There was a problem hiding this comment.
this we can discuss
| requires-python = ">=3.8,<3.11" | ||
| dependencies = [ | ||
| "transformers==4.55.0", | ||
| "transformers==4.57.0", |
There was a problem hiding this comment.
Yes we should raise it, and start the run of all the models with 4.57 in parallel, typically it takes 1week.
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dhiraj Kumar Sah <dhirajku@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
| QEffMptForCausalLM, | ||
| QEffPhi3ForCausalLM, | ||
| QEffQwen2ForCausalLM, | ||
| QEffQwen_2_5_vl_DecoderWrapper, |
There was a problem hiding this comment.
Could you add QEffQwen3VLDecoderWrapper here under SamplerTransform? The on-device sampling is generic, so it can support new VLMs. Thank you.
If not, we can also raise a new patch @quic-sanising
6 participants
Adding Qwen3VL Support to QEff