Skip to content

Pull requests: huggingface/optimum-quanto

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
Assignee
Filter by who’s assigned
Sort

Pull requests list

Extension lifecycle
#223 by dacorvo was merged Jun 28, 2024 Loading…
Add QuantizedModelForCausalLM
#243 by dacorvo was merged Jul 17, 2024 Loading…
Add marlin int4 kernel
#315 by dacorvo was closed Sep 27, 2024 Draft
Add latest AWQ CUDA fp16 int4 kernels
#198 by dacorvo was merged May 23, 2024 Loading…
Support Quantization Aware Training for QLinear
#3 by dacorvo was merged Oct 3, 2023 Loading…
Add quantize method and MNIST basic example
#4 by dacorvo was merged Oct 4, 2023 Loading…
Add freeze() method and test quantization-aware training
#5 by dacorvo was merged Oct 6, 2023 Loading…
Add model serialization test and examples
#6 by dacorvo was merged Oct 6, 2023 Loading…
fix(library): Propagate upstream Marlin kernel fix Stale
#366 by ahadnagy was closed Jan 29, 2025 Loading…
3 of 4 tasks
Refactor qtensor
#8 by dacorvo was merged Oct 6, 2023 Loading…
Hot fix
#9 by dacorvo was merged Oct 6, 2023 Loading…
fix(setup): add missing packages
#11 by dacorvo was merged Oct 9, 2023 Loading…
chore: bump version
#12 by dacorvo was merged Oct 9, 2023 Loading…
Use MPS device whenever available in tests and examples
#15 by dacorvo was merged Oct 9, 2023 Loading…
chore: version 0.0.5
#17 by dacorvo was merged Oct 19, 2023 Loading…
Add basic mechanism to register a quantized module
#18 by dacorvo was merged Oct 20, 2023 Loading…
Add text-generation example with an OPT model
#20 by dacorvo was merged Oct 24, 2023 Loading…
A few fixes
#22 by dacorvo was merged Oct 25, 2023 Loading…
More fixes
#23 by dacorvo was merged Oct 26, 2023 Loading…
Generic generation example
#24 by dacorvo was merged Oct 26, 2023 Loading…
Set strides explicitly when creating a QTensor
#26 by dacorvo was merged Oct 26, 2023 Loading…
More ops
#27 by dacorvo was merged Oct 27, 2023 Loading…
Add a codegen example
#28 by dacorvo was merged Oct 27, 2023 Loading…
Support transformer models
#16 by dacorvo was merged Oct 17, 2023 Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.