Skip to content

Pull requests: quic/efficient-transformers

New pull request New
26 Open 488 Closed
26 Open 488 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Update PyTorch to 2.7.0+cpu, Torchvision to 0.22.0+cpu, and Python Requirement to >=3.9
#524 opened Jul 28, 2025 by abukhoy Loading…
1
Add Support for Frequency Penalties in On Device Sampling
#523 opened Jul 24, 2025 by quic-sanising • Draft
1
Deleted model after export to save memory
#521 opened Jul 22, 2025 by asmigosw • Draft
[QEff. Finetune] Updated handling of custom dataset in FT. Updated finetune.md readme file.
#520 opened Jul 21, 2025 by quic-meetkuma Loading…
10
Logger module in Efficient Transformers 1.21.0 wip Work in progress
#517 opened Jul 11, 2025 by quic-hemagnih • Draft
@quic-hemagnih
7
Added MIN_MASKED_ATTENTION_VALUE
#513 opened Jul 10, 2025 by quic-amitraj Loading…
1
Added --iteration and --automation flags
#512 opened Jul 10, 2025 by asmigosw • Draft
@asmigosw
Llama4 VLM Continuous Batching Support
#510 opened Jul 9, 2025 by mohiso22 Loading…
@mohiso22
[Olmo2]: Add Support for Olmo2 CausalLM Model in QEff 1.21.0 enhancement New feature or request
#509 opened Jul 9, 2025 by vbaddi Loading…
@vbaddi
Jina model support [experimental]
#502 opened Jul 8, 2025 by quic-amitraj • Draft
Hybrid chunked cache update
#500 opened Jul 8, 2025 by quic-amitraj • Draft
Reading mxfp6_matmul for QNN Compilation path from compile API arguments 1.21.0
#499 opened Jul 7, 2025 by shubhagr-qc Loading…
@shubhagr-qc
default NPI file added 1.21.0
#498 opened Jul 7, 2025 by quic-akuruvil Loading…
@quic-akuruvil
[Llama4]: Add support for padding num_patches 1.21.0 enhancement New feature or request
#486 opened Jul 1, 2025 by vbaddi Loading…
@vbaddi
Changing the hashing methodology for cache folder creation of models. 1.21.0
#481 opened Jun 24, 2025 by quic-dhirajku Loading…
18
adding Context Length Specialization (CCL) 1.21.0
#466 opened Jun 19, 2025 by quic-vjanfaza Loading…
7
Unit Tests for On Device Sampling 1.21.0
#463 opened Jun 18, 2025 by quic-sanising Loading…
20
Updated get_available_device_id logic 1.21.0
#445 opened Jun 11, 2025 by quic-rishinr Loading…
[Tests]: Adding dummy causal models for testing in regular CI run 1.21.0 ready for review
#427 opened May 29, 2025 by abukhoy Loading…
@abukhoy
42
Added Prompt length check for VLMs
#422 opened May 21, 2025 by asmigosw Loading…
1
Qwen3moe model-enablement
#406 opened May 15, 2025 by qcdipankar Loading…
@qcdipankar
9
Added inference per sec for AutoModel
#405 opened May 15, 2025 by quic-amitraj • Draft
3
Add Onnx Accuracy Utility Script enhancement New feature or request
#366 opened Apr 16, 2025 by vbaddi • Draft
@vbaddi
1
Onboarding Mistral3.1_24B 1.21.0 model-enablement
#358 opened Apr 11, 2025 by mohiso22 Loading…
@mohiso22
1
feat: Add option to pass QAICInferenceSession to TextGeneration
#356 opened Apr 11, 2025 by quic-shagun Loading…
9
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.