"git@developer.sourcefind.cn:change/sglang.git" did not exist on "7d121448b21ca05a2700e8e74f3fced179061af0"
- 15 Mar, 2025 1 commit
-
-
Dimitri Barbot authored
Co-authored-by:Dhruv Nair <dhruv.nair@gmail.com>
-
- 14 Mar, 2025 3 commits
-
-
Juan Acevedo authored
reverts accidental change that removes attn_mask in attn. Improves flux ptxla by using flash block sizes. Moves encoding outside the for loop. Co-authored-by:Juan Acevedo <jfacevedo@google.com>
-
Sayak Paul authored
feat: support non-diffusers wan t2v loras.
-
Sayak Paul authored
* restrict memory tests for quanto for certain schemes. * Apply suggestions from code review Co-authored-by:
-
- 13 Mar, 2025 2 commits
-
-
ZhengKai91 authored
* get_1d_rotary_pos_embed support npu * Update src/diffusers/models/embeddings.py --------- Co-authored-by:
Kai zheng <kaizheng@KaideMacBook-Pro.local> Co-authored-by:
hlky <hlky@hlky.ac> Co-authored-by:
YiYi Xu <yixu310@gmail.com>
-
hlky authored
* Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline --------- Co-authored-by:
-
- 12 Mar, 2025 5 commits
-
-
Sayak Paul authored
* move to warning. * test related changes.
-
hlky authored
* Wan Pipeline scaling fix, type hint warning, multi generator fix * Apply suggestions from code review
-
hlky authored
* [hybrid inference
🍯 🐝 ] Add VAE encode * _toctree: add vae encode * Add endpoints, tests * vae_encode docs * vae encode benchmarks * api reference * changelog * Update docs/source/en/hybrid_inference/overview.md Co-authored-by:Sayak Paul <spsayakpaul@gmail.com> * update --------- Co-authored-by:
-
hlky authored
-
Dhruv Nair authored
* update * update * update
-
- 11 Mar, 2025 5 commits
-
-
Ensure that hidden_state and shift/scale are on the same device when running with multiple GPUs Co-authored-by: Jimmy <39@
🇺🇸 .com> -
CyberVy authored
* Update lora_pipeline.py * Apply style fixes * fix-copies --------- Co-authored-by:
github-actions[bot] <github-actions[bot]@users.noreply.github.com>
-
hlky authored
-
Sayak Paul authored
* support wan i2v loras from the world. * remove copied from. * upates * add lora.
-
Dhruv Nair authored
* update * update * update * update * update * update * update * update * update
-
- 10 Mar, 2025 6 commits
-
-
Sayak Paul authored
* memory usage tests * fixes * gguf
-
Aryan authored
* update * make fix-copies * update
-
Sayak Paul authored
* updates * updates * updates * updates * notebooks revert * fix-copies. * seeing * fix * revert * fixes * fixes * fixes * remove print * fix * conflicts ii. * updates * fixes * better filtering of prefix. --------- Co-authored-by: -
Ishan Modi authored
* added support for from_single_file * added diffusers mapping script * added testcase * bug fix * updated tests * corrected code quality * corrected code quality --------- Co-authored-by: -
Dhruv Nair authored
* update * updaet * update * update * update * update * update * update * update * update * update * update * Update docs/source/en/quantization/quanto.md Co-authored-by:
-
Dhruv Nair authored
* update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update
-
- 08 Mar, 2025 1 commit
-
-
Sayak Paul authored
* more sanity of mind with copied from ... * better * better
-
- 07 Mar, 2025 6 commits
-
-
Dhruv Nair authored
* update * update * update * update * update * update * update
-
Sayak Paul authored
remove full key prefix from peft.
-
hlky authored
-
C authored
* Fix Graph Breaks When Compiling CogView4 Eliminate this: ``` t]V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] Recompiling function forward in /home/zeyi/repos/diffusers/src/diffusers/models/transformers/transformer_cogview4.py:374 V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] triggered by the following guard failure(s): V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] - 0/3: ___check_obj_id(L['self'].rope.freqs_h, 139976127328032) V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] - 0/2: ___check_obj_id(L['self'].rope.freqs_h, 139976107780960) V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] - 0/1: ___check_obj_id(L['self'].rope.freqs_h, 140022511848960) V0304 10:24:23.421000 3131076 torch/_dynamo/guards.py:2813] [0/4] [__recompiles] - 0/0: ___check_obj_id(L['self'].rope.freqs_h, 140024081342416) ``` * Update transformer_cogview4.py * fix cogview4 rotary pos embed * Apply style fixes --------- Co-authored-by:
-
Aryan authored
* update * update * update * add tests * update * add model tests * update docs * update * update example * fix defaults * update
-
yupeng1111 authored
* fix wan i2v pipeline bugs --------- Co-authored-by:
-
- 06 Mar, 2025 4 commits
-
-
Dhruv Nair authored
update
-
CyberVy authored
* Update pipeline_flux_controlnet.py * Update pipeline_flux_controlnet_image_to_image.py * Update pipeline_flux_controlnet_inpainting.py * Update pipeline_flux_controlnet_inpainting.py * Update pipeline_flux_controlnet_inpainting.py
-
Pierre Chapuis authored
-
hlky authored
Co-authored-by:
-
- 04 Mar, 2025 7 commits
-
-
YiYi Xu authored
fix
-
Yuxuan Zhang authored
* Update pipeline_cogview4.py * Use GLM instead of T5 in doc
-
Aryan authored
* update * refactor image-to-video pipeline * update * fix copied from * use FP32LayerNorm
-
CyberVy authored
Update quantization_config.py
-
a120092009 authored
* [Quantization] support pass MappingType for TorchAoConfig * Apply style fixes --------- Co-authored-by: -
Sayak Paul authored
* feat: support non-diffusers lumina2 LoRAs. * revert ipynb changes (but I don't know why this is required
☹ ️) * empty --------- Co-authored-by: -
CyberVy authored
* Update ip_adapter.py * Update ip_adapter.py * Update ip_adapter.py * Update ip_adapter.py * Update ip_adapter.py * Apply style fixes --------- Co-authored-by:
-
