Skip to content

Pull requests: quic/efficient-transformers

New pull request New
45 Open 735 Closed
45 Open 735 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

[QEff.finetuning] Hf config update
#792 opened Feb 11, 2026 by tchawada Loading…
MLA
#789 opened Feb 10, 2026 by quic-mamta Loading…
Wan I2V support
#788 opened Feb 10, 2026 by tv-karthikeya • Draft
Updating Wan Vae pytest, Export to 45p, minor issues
#783 opened Feb 9, 2026 by tv-karthikeya Loading…
1
Upgrade python version from 3.10 to 3.12
#782 opened Feb 9, 2026 by quic-rishinr Loading…
Updating wav2vec2_inference for batched_input
#781 opened Feb 9, 2026 by tchawada Loading…
Onboarding Qwen3VL Dense model-enablement
#780 opened Feb 6, 2026 by qcdipankar Loading…
@qcdipankar @quic-dhirajku
26
removed duplication of mdp_json_path in compilation command (#706)
#779 opened Feb 5, 2026 by ochougul Loading…
5
Fixing the issue of CCL support during the decoding phase of Disaggregated Serving
#776 opened Feb 5, 2026 by vjanfaza Loading…
1
WIP: Enabled fp16/bf16 based export and compile for some causalLMs.
#775 opened Feb 3, 2026 by quic-dhirajku • Draft
feat(QEff: Attn): add KV & Q blocking strategies for causal LMs enhancement New feature or request qeff.blocking
#774 opened Feb 3, 2026 by vbaddi • Draft
3 tasks
@kdulla @vbaddi
Fixed Granite_moe and added to CI
#771 opened Feb 2, 2026 by quic-akuruvil Loading…
2
Accuracy Onboarding - This is a test template wip Work in progress
#767 opened Jan 29, 2026 by abisravi777-hub • Draft
@abisravi777-hub
1
Fix for CB incosistency for qwen2_5_vl
#765 opened Jan 29, 2026 by asmigosw • Draft
1
Adding support for multi_vision Specialization in qwen2_5_vl
#755 opened Jan 23, 2026 by mohiso22 • Draft
["QEff.finetuning"] Inference script for HF_trainer
#749 opened Jan 21, 2026 by tchawada Loading…
Adding blocked kv and skip softmax for gpt oss
#745 opened Jan 20, 2026 by kdulla • Draft
@kdulla
[Qeff.finetuning] Adding Full document for hf_based finetuning stack
#732 opened Jan 16, 2026 by tchawada Loading…
5
[QEff. Finetuning] Adding finetune_experiemental.py and related files
#731 opened Jan 16, 2026 by quic-swatia Loading…
36
Adding the support of dense models distilled from moe models with the same architecture
#728 opened Jan 16, 2026 by vjanfaza Loading…
1
Added changes to load and export Llama model in bfloat16/float16 precision
#707 opened Jan 7, 2026 by quic-dhirajku • Draft
Flux rotary embedding changes
#705 opened Jan 6, 2026 by quic-amitraj • Draft
[QEff. Finetuning] Loading HF models partially to save testing compute
#704 opened Jan 6, 2026 by quic-swatia Loading…
Subfunction fix: changed invalid_index to INT32MAX Always
#700 opened Jan 5, 2026 by abhishek-singh591 Loading…
2
Logger Module For Efficient Transformers
#696 opened Jan 2, 2026 by abhishek-singh591 Loading…
ProTip! no:milestone will show everything without a milestone.