Add test for deepseek_vl with cache #1332
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
meenakshiramanathan1
requested review from
vkovinicTT,
mstojkovicTT,
nvukobratTT,
pilkicTT and
dgolubovicTT
as code owners
|
||||||||||||||||||
3 similar comments
|
||||||||||||||||||
|
||||||||||||||||||
|
||||||||||||||||||
meenakshiramanathan1
force-pushed
the
mramanathan/deepseek_kv_cache
branch
from
ec38d96 to
ada5510
Compare
|
||||||||||||||
1 similar comment
|
||||||||||||||
|
||||||||||||||
1 similar comment
|
||||||||||||||
ashokkumarkannan1
requested changes
Feb 27, 2025
| vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True) | ||
| vl_gpt = vl_gpt.eval() | ||
|
|
||
| class Wrapper(torch.nn.Module): |
There was a problem hiding this comment.
Pls move this Wrapper class outside the function.
| def calculate_attention_mask_and_postion_ids( | ||
| padded_past_key_values_seq_length, non_padding_past_key_values_seq_length, input_seq_length | ||
| ): | ||
|
|
There was a problem hiding this comment.
Add a comment why we are doing this here
| model_inputs[1][idx][0][:, :, non_padding_past_key_values_seq_length, :] = model_inputs[1][idx][0][ | ||
| :, :, -1, : | ||
| ] | ||
| logger.info(f"shape of key_tensor = {model_inputs[1][idx][0].shape}") |
There was a problem hiding this comment.
remove logger statements
Comment on lines
+180
to
+188
| tt_output = [tt_out.to("cpu") for tt_out in tt_output] | ||
|
|
||
| # Validate TT result with Framework | ||
| assert all( | ||
| [ | ||
| compare_with_golden(golden=fw_out, calculated=tt_out) | ||
| for fw_out, tt_out in zip(framework_output, tt_output) | ||
| ] | ||
| ) |
There was a problem hiding this comment.
let's use verify function
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Model is failing with runtime error - issue
E RuntimeError: TT_THROW @ /proj_sw/user_dev/mramanathan/bgdlab07_feb26_forge/tt-forge-fe/third_party/tt-mlir/third_party/tt-metal/src/tt-metal/ttnn/cpp/ttnn/operations/eltwise/binary/device/broadcast_height_and_width_multi_core_program_factory.cpp:27: tt::exception E info: E BinaryOpType cannot be mapped to BcastOpMath