Skip to content

Issues: huggingface/optimum-quanto

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

18 Open 112 Closed
18 Open 112 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Static Quantization - Weights Still in FP32
#347 opened Nov 6, 2024 by ClaraLovesFunk
1
How to support activation 4bit quantization?
#346 opened Nov 4, 2024 by Ther-nullptr
1
Only random noise is generated with Flux + LoRA with optimum-quanto >= 0.2.5
#343 opened Oct 30, 2024 by nelapetrzelkova
Inference Speed Slowdown with Static Quantization
#340 opened Oct 29, 2024 by ClaraLovesFunk
2
Will module output not be quantized when the model is directly trained after Calibration?
#336 opened Oct 11, 2024 by tusiqi1
5
Corrupted outputs with Marlin int4 kernels as parallelization increases bug Something isn't working help wanted Extra attention is needed
#332 opened Oct 6, 2024 by dacorvo
3
optimum-quanto 0.25 requires ninja but 'pip check flux' reports 'ninja-1.11.1.1 is not supported on this platform' Stale
#331 opened Oct 5, 2024 by Davros666
1
Accuracy issue when using torch._int_mm on AMD CPUs
#319 opened Sep 26, 2024 by dacorvo
2
qint4 failed for diffusers: QBitsTensor cannot be changed
#312 opened Sep 19, 2024 by liyihao1230
1
qin4 inference fails with RuntimeError: Cannot set version_counter for inference tensor
#304 opened Sep 3, 2024 by BenjaminBossan
8
Potential Gradient Error when Reloading Frozen Weights in qmodule.py _load_from_state_dict Stale
#293 opened Aug 24, 2024 by cjfghk5697
3
Support for FP8 Matmuls
#275 opened Aug 9, 2024 by maktukmak
2
Support for new diffuser: flux1.schnell
#272 opened Aug 7, 2024 by KoppAlexander
@dacorvo
6
Packages created on the CI are missing cpp and cuda extension files
#254 opened Jul 23, 2024 by dacorvo
5
qint4 failing with PixArt Transformer
#228 opened Jul 3, 2024 by sayakpaul
9
Inference from a reload quantized open clip model (by .load_state_dict) resulted in IndexError Stale
#217 opened Jun 24, 2024 by kechan
@dacorvo
8
Switch to ruff native formatter good first issue Good for newcomers help wanted Extra attention is needed Stale
#186 opened Apr 22, 2024 by dacorvo
11
QTensor cannot be created from inside a dynamo graph
#46 opened Dec 11, 2023 by dacorvo
9
ProTip! Type g i on any issue or pull request to go back to the issue listing page.