Skip to content

Pull requests: neuralmagic/compressed-tensors

New pull request New
17 Open 296 Closed
17 Open 296 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

[Misc] Remove unused config name definitions
#332 opened May 31, 2025 by kylesayrs Loading…
[NVFP4] Use torch.compile when rounding to NVFP4
#331 opened May 30, 2025 by dsikka Loading…
1
[Transform] Hadamard and Matrix Transform Utils
#330 opened May 30, 2025 by kylesayrs Loading…
[Transform] Hadamard Permutations
#329 opened May 30, 2025 by kylesayrs Loading…
[Transform] Accelerate Utilities
#328 opened May 30, 2025 by kylesayrs Loading…
2
Make MSE the default
#324 opened May 22, 2025 by dsikka Loading…
4
Model Compression: Delete offload
#319 opened May 19, 2025 by kylesayrs Loading…
1
[Transform] Factory classes with shared memory and offloading
#316 opened May 15, 2025 by kylesayrs Loading…
[NVFP4][WIP] Add NVFp4 Support
#287 opened Mar 31, 2025 by dsikka • Draft
2
[Transforms][WIP] Update wrapped_forward to use hooks; apply transforms to activations
#286 opened Mar 31, 2025 by dsikka • Draft
1
[Transforms] Enable shared memory and introduce permutations
#284 opened Mar 26, 2025 by dsikka Loading…
11
[Transforms] Initial Implementation
#277 opened Mar 11, 2025 by dsikka Loading…
[Transforms] Apply, serialize, deserialize
#276 opened Mar 11, 2025 by dsikka Loading…
6
[Transforms] Transform Registry Support
#274 opened Mar 11, 2025 by dsikka Loading…
31
[Quantization] Channel wise output activation quantization for QKV Attention layers
#270 opened Mar 7, 2025 by horheynm • Draft
Harden KV Cache qparams
#262 opened Feb 26, 2025 by kylesayrs • Draft
3
move llmcompressor util is_model_path_quantized to ct
#246 opened Jan 24, 2025 by horheynm Loading…
8
ProTip! Adding no:label will show everything without a label.