transformers/docs/source/en
Jerry Zhang 2af272c101
Add autoquant support for torchao quantizer (#35503)
* Add autoquant support for torchao quantizer

Summary:
att, also verified that autoquantized model can be saved and loaded:

save: https://gist.github.com/jerryzh168/01d367aaf44dbbbfd4068a4a10a00061
load: https://gist.github.com/jerryzh168/d5c6c401b2abdf18e0b6771341f1525c

Test Plan:
tested locally with above script
model uploaded to https://huggingface.co/jerryzh168/llama3-8b-autoquant

Reviewers:

Subscribers:

Tasks:

Tags:

* add test

* ruff fix

* ruff reformat

* add docs and min_sqnr support

* format

* format

* fix test

* update doc

* format

* remove disable_compile

* format
2025-02-24 15:54:16 +01:00
..
internal Implement AsyncTextIteratorStreamer for asynchronous streaming (#34931) 2024-12-20 12:08:12 +01:00
main_classes Efficient Inference Kernel for SpQR (#34976) 2025-02-13 16:22:58 +01:00
model_doc Add SigLIP 2 (#36323) 2025-02-21 09:04:19 +00:00
quantization Add autoquant support for torchao quantizer (#35503) 2025-02-24 15:54:16 +01:00
tasks Move DataCollatorForMultipleChoice from the docs to the package (#34763) 2025-02-13 12:01:28 +01:00
_config.py Add optimized PixtralImageProcessorFast (#34836) 2024-11-28 16:04:05 +01:00
_redirects.yml Docs / Quantization: Redirect deleted page (#31063) 2024-05-28 18:29:22 +02:00
_toctree.yml Add SigLIP 2 (#36323) 2025-02-21 09:04:19 +00:00
accelerate.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
add_new_model.md Model addition timeline (#33762) 2024-09-27 17:15:13 +02:00
add_new_pipeline.md [docs] Follow up register_pipeline (#35310) 2024-12-20 09:22:44 -08:00
agents_advanced.md [doctest] Fixes (#35863) 2025-01-26 15:26:38 -08:00
agents.md Multiple typo fixes in Tutorials docs (#35035) 2024-12-02 15:26:34 +00:00
attention.md [Docs] Fix broken links and syntax issues (#28918) 2024-02-08 14:13:35 -08:00
autoclass_tutorial.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
bertology.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
big_models.md [docs] Big model loading (#29920) 2024-04-01 18:47:32 -07:00
chat_template_advanced.md Chat template docs (#36163) 2025-02-14 10:32:14 +01:00
chat_template_basics.md Chat template docs (#36163) 2025-02-14 10:32:14 +01:00
chat_template_multimodal.md Chat template docs (#36163) 2025-02-14 10:32:14 +01:00
chat_template_tools_and_documents.md Chat template docs (#36163) 2025-02-14 10:32:14 +01:00
community.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
contributing.md Enable doc in Spanish (#16518) 2022-04-04 10:25:46 -04:00
conversations.md [docs] change temperature to a positive value (#32077) 2024-07-23 17:47:51 +01:00
create_a_model.md Enable HF pretrained backbones (#31145) 2024-06-06 22:02:38 +01:00
custom_models.md Updated the custom_models.md changed cross_entropy code (#33118) 2024-08-26 13:15:43 +02:00
debugging.md DeepSpeed github repo move sync (#36021) 2025-02-05 08:19:31 -08:00
deepspeed.md DeepSpeed github repo move sync (#36021) 2025-02-05 08:19:31 -08:00
fast_tokenizers.md Migrate doc files to Markdown. (#24376) 2023-06-20 18:07:47 -04:00
fsdp.md Fix docs typos. (#35465) 2025-01-02 11:29:46 +01:00
generation_strategies.md [doctest] Fixes (#35863) 2025-01-26 15:26:38 -08:00
gguf.md Add Gemma2 GGUF support (#34002) 2025-01-03 14:50:07 +01:00
glossary.md Fix typos (#31819) 2024-07-08 11:52:47 +01:00
how_to_hack_models.md Add utility for Reload Transformers imports cache for development workflow #35508 (#35858) 2025-02-12 12:45:11 +01:00
hpo_train.md Trainer - deprecate tokenizer for processing_class (#32385) 2024-10-02 14:08:46 +01:00
index.md Add SigLIP 2 (#36323) 2025-02-21 09:04:19 +00:00
installation.md [docs] uv install (#35821) 2025-01-27 08:49:28 -08:00
kv_cache.md [docs] no hard-coding cuda (#36043) 2025-02-05 08:22:33 -08:00
llm_optims.md Update llm_optims docs for sdpa_kernel (#35481) 2025-01-06 08:54:31 -08:00
llm_tutorial_optimization.md feat: add support for tensor parallel training workflow with accelerate (#34194) 2025-02-18 14:05:46 +01:00
llm_tutorial.md [docs] no hard coding cuda as bnb has multi-backend support (#35867) 2025-02-05 08:20:02 -08:00
model_memory_anatomy.md Enable BNB multi-backend support (#31098) 2024-09-24 03:40:56 -06:00
model_sharing.md [docs] update not-working model revision (#34682) 2024-11-11 07:09:31 -08:00
model_summary.md model_summary.md - Restore link to Harvard's Annotated Transformer. (#29702) 2024-03-23 18:29:39 -07:00
modular_transformers.md Improve modular documentation (#35737) 2025-01-21 17:53:30 +01:00
multilingual.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
notebooks.md Enable doc in Spanish (#16518) 2022-04-04 10:25:46 -04:00
pad_truncation.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
peft.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
perf_hardware.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
perf_infer_cpu.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
perf_infer_gpu_multi.md Update doc re list of models supporting TP (#35864) 2025-02-12 15:53:27 +01:00
perf_infer_gpu_one.md Add SigLIP 2 (#36323) 2025-02-21 09:04:19 +00:00
perf_torch_compile.md [docs] use device-agnostic instead of cuda (#35047) 2024-12-03 10:53:45 -08:00
perf_train_cpu_many.md [doc] use full path for run_qa.py (#34914) 2024-11-26 09:23:44 -08:00
perf_train_cpu.md [doc] use full path for run_qa.py (#34914) 2024-11-26 09:23:44 -08:00
perf_train_gpu_many.md feat: add support for tensor parallel training workflow with accelerate (#34194) 2025-02-18 14:05:46 +01:00
perf_train_gpu_one.md layernorm_decay_fix (#35927) 2025-02-04 11:01:49 +01:00
perf_train_special.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_train_tpu_tf.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
performance.md Simplify Tensor Parallel implementation with PyTorch TP (#34184) 2024-11-18 19:51:49 +01:00
perplexity.md [docs] use device-agnostic API instead of cuda (#34913) 2024-11-26 09:23:34 -08:00
philosophy.md [docs] fixed links with 404 (#27327) 2023-11-06 19:45:03 +00:00
pipeline_tutorial.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
pipeline_webserver.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
pr_checks.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
preprocessing.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
quicktour.md [chat] docs fix (#35840) 2025-01-22 14:32:27 +00:00
run_scripts.md [docs] refine the doc for train with a script (#33423) 2024-09-12 10:16:12 -07:00
sagemaker.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
serialization.md [docs] fix model checkpoint name (#36075) 2025-02-07 12:41:52 -08:00
task_summary.md [doctest] Fixes (#35863) 2025-01-26 15:26:38 -08:00
tasks_explained.md fix: Wrong task mentioned in docs (#34757) 2024-11-18 18:42:28 +00:00
testing.md [tests] add XPU part to testing (#34778) 2024-11-18 09:59:11 -08:00
tf_xla.md fix(docs): Fixed a link in docs (#32274) 2024-07-29 10:50:43 +01:00
tflite.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
tiktoken.md Updated documentation and added conversion utility (#34319) 2024-11-25 18:44:09 +01:00
tokenizer_summary.md [docs] Spanish translation of tokenizer_summary.md (#31154) 2024-06-03 16:52:23 -07:00
torchscript.md Fixed Majority of the Typos in transformers[en] Documentation (#33350) 2024-09-09 10:47:24 +02:00
trainer.md feat: add support for tensor parallel training workflow with accelerate (#34194) 2025-02-18 14:05:46 +01:00
training.md [docs] Increase visibility of torch_dtype="auto" (#35067) 2024-12-04 09:18:44 -08:00
troubleshooting.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00