added git workflow for unittest#23
Open
quic-rishinr wants to merge 15 commits into
Open
Conversation
quic-rishinr
force-pushed
the
unit_test_workflow
branch
3 times, most recently
from
f29d4bf to
078b0b9
Compare
quic-rishinr
force-pushed
the
unit_test_workflow
branch
from
f1577e6 to
e36bf6c
Compare
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
quic-rishinr
force-pushed
the
unit_test_workflow
branch
from
e36bf6c to
941fd3f
Compare
… align the subfunction changes. (#882) This PR rebases dev/rebase_transformers_v4_57_3 onto main and consolidates our transformer rebase changes with the PR #880 subfunction/KV alignment so we keep the branch simpler and unify the subfunction approach. ### What changed - KV/subfunction alignment: - Applied PR #880-style wrapper changes for causal model families to reduce divergence from mainline. - Removed local resolve_kv_seq_len usage from remaining wrappers (grok_1, molmo) to match the cache-native pattern used elsewhere. - Removed now-unused helper resolve_kv_seq_len from QEfficient/utils/_utils.py. - Unit test updates: - Added a new quickcheck unit test for use_onnx_subfunctions=True that validates decoder-block subfunction cardinality per causal model. - Important: test counts only decoder model block functions (via get_submodules_for_export()), not all ONNX helper functions, so the assertion tracks the intended behavior. ### Decoder-block subfunction status (causal model list) - Single decoder-block subfunction: falcon, gpt2, gptj, granite, llama, mistral, mpt, olmo2, phi3, qwen2 - Multiple decoder-block subfunctions: codegen, gpt_oss, mixtral, phi (Phi-1), starcoder2 ### Tests verified ``` python -m pytest -q tests/unit_test/models/test_model_quickcheck.py -n auto Result after subfunction-count + KV-helper cleanup: 75 passed, 1 skipped ``` cc: @anujgupt-github @quic-hemagnih --------- Signed-off-by: vbaddi <vbaddi@qti.qualcomm.com> Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com> Signed-off-by: abhishek-singh591 <sabhis@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com> Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com> Co-authored-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com> Co-authored-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Co-authored-by: Mamta Singh <mamtsing@qti.qualcomm.com> Co-authored-by: vtirumal <vtirumal@qti.qualcomm.com>
1. Added Support for Qwen3-VL 2. Added Support for Qwen3-VL-Moe 3. Added Support for Disaggregated VL MOE Model. (Three QPC ) 4. CB support --------- Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <quic_dipankar@quicinc.com> Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com> Signed-off-by: Dhiraj Kumar Sah <dhirajku@qti.qualcomm.com> Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com> Co-authored-by: Onkar Chougule <168134249+ochougul@users.noreply.github.com> Co-authored-by: Dhiraj Kumar Sah <dhirajku@qti.qualcomm.com> Co-authored-by: vtirumal <vtirumal@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Updating wav2vec2 for batched_input and adding args for parsing
batch_size, ctx_len and num_devices
model.compile(batch_size=args.batch_size,
num_devices=args.num_devices,
seq_len=args.seq_len,
num_cores=args.num_cores)
---------
Signed-off-by: Tanisha Chawada <tchawada@qti.qualcomm.com>
to allow authenticated access to gated HuggingFace models - Wrap model/tokenizer loading in try/except blocks in quickcheck tests to gracefully skip tests when model fetch fails (e.g., auth errors) - Fix HybridChunkedCache backward compatibility for transformers>=4.57 which no longer exposes key_cache/value_cache attributes - Fix Gemma3 config compatibility by mapping _sliding_window_pattern to sliding_window_pattern when the public attribute is missing Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
No description provided.