Commit Graph

83 Commits

Author SHA1 Message Date
Matthew Douglas
e447185b1f
Fix bnb training test failure (#34414)
* Fix bnb training test: compatibility with OPTSdpaAttention
2024-10-25 10:23:20 -04:00
김준재
dd267fca72
Add T5 GGUF loading support (#33389)
* add: GGUFT5Converter

* add: tensormapping for t5

* add: test code for t5

* fix: Remove whitespace from blank line

* add: t5 fp16 tests

* fix: whitespace formatting

* fix: minor formatting

* fix: testing every weights
2024-10-24 15:10:59 +02:00
Vladislav Bronzov
cb5ca3265f
Add GGUF for starcoder2 (#34094)
* add starcoder2 arch support for gguf

* fix q6 test
2024-10-14 10:22:49 +02:00
Vladislav Bronzov
c9afee5392
Add gguf support for gpt2 (#34044)
* add gpt2 gguf support

* add doc change

* small refactoring
2024-10-10 13:42:18 +02:00
Mohamed Mekkouri
36d410dab6
FEAT : Adding BitNet quantization method to HFQuantizer (#33410)
* rebasing changes

* fixing style

* adding some doc to functions

* remove bitblas

* change dtype

* fixing check_code_quality

* fixing import order

* adding doc to tree

* Small update on BitLinear

* adding some tests

* sorting imports

* small update

* reformatting

* reformatting

* reformatting with ruff

* adding assert

* changes after review

* update disk offloading

* adapting after review

* Update after review

* add is_serializable back

* fixing style

* adding serialization test

* make style

* small updates after review
2024-10-09 17:51:41 +02:00
Vladislav Bronzov
faa0f63b93
Add gguf support for StableLM (#33793)
* add stablelm gguf architecture support

* add additional quantization tests

* resolve merge conflict, add weight conversion tests for fp16
2024-10-09 12:16:13 +02:00
Vladislav Bronzov
22e102ad98
Bug fix gguf qwen2moe (#33940)
* fix qwen2moe tensors mapping, add unit tests

* add expert tensor split logic, test refactoring

* small params refactoring

* add comment to tensor reshaping
2024-10-05 16:19:01 +02:00
jiqing-feng
b916efcb3c
Enables CPU AWQ model with IPEX version. (#33460)
* enable cpu awq ipex linear

* add doc for cpu awq with ipex kernel

* add tests for cpu awq

* fix code style

* fix doc and tests

* Update docs/source/en/quantization/awq.md

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update tests/quantization/autoawq/test_awq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* fix comments

* fix log

* fix log

* fix style

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
2024-10-04 16:25:10 +02:00
Marc Sun
cac4a4876b
[Quantization] Switch to optimum-quanto (#31732)
* switch to optimum-quanto rebase squach

* fix import check

* again

* test try-except

* style
2024-10-02 15:14:34 +02:00
g-prz
fe484726aa
Add falcon gguf (#33437)
* feat(gguf): add falcon q2 k

* fix(gguf): remove useless renaming

* feat(gguf): seperate falcon 7b and 40b

* feat(gguf): apply fixup

* fix(test): error rebase

* feat(gguf): add fp16 weight comparison for falcon

* feat(gguf): test weight of all layers

* test(gguf): add falcon 40b under skip decorator

* feat(gguf): quick example for extracting model size
2024-10-02 14:10:39 +02:00
mobicham
f5247aca01
Hqq serialization (#33141)
* HQQ model serialization attempt

* fix hqq dispatch and unexpected keys

* style

* remove check_old_param

* revert to check HQQLinear in quantizer_hqq.py

* revert to check HQQLinear in quantizer_hqq.py

* update HqqConfig default params

* make ci happy

* make ci happy

* revert to HQQLinear check in quantizer_hqq.py

* check hqq_min version 0.2.0

* set axis=1 as default in quantization_config.py

* validate_env with hqq>=0.2.0 version message

* deprecated hqq kwargs message

* make ci happy

* remove run_expected_keys_check hack + bump to 0.2.1 min hqq version

* fix unexpected_keys hqq update

* add pre_quantized check

* add update_expected_keys to base quantizerr

* ci base.py fix?

* ci base.py fix?

* fix "quantization typo" src/transformers/utils/quantization_config.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fix post merge

---------

Co-authored-by: Marc Sun <marc@huggingface.co>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2024-09-30 14:47:18 +02:00
Vladislav Bronzov
9d200cfbee
Add gguf support for bloom (#33473)
* add bloom arch support for gguf

* apply format

* small refactoring, bug fix in GGUF_TENSOR_MAPPING naming

* optimize bloom GGUF_TENSOR_MAPPING

* implement reverse reshaping for bloom gguf

* add qkv weights test

* add q_8 test for bloom
2024-09-27 12:13:40 +02:00
Benjamin Fineran
574a9e12bb
HFQuantizer implementation for compressed-tensors library (#31704)
* Add compressed-tensors HFQuantizer implementation

* flag serializable as False

* run

* revive lines deleted by ruff

* fixes to load+save from sparseml, edit config to quantization_config, and load back

* address satrat comment

* compressed_tensors to compressed-tensors and revert back is_serializable

* rename quant_method from sparseml to compressed-tensors

* tests

* edit tests

* clean up tests

* make style

* cleanup

* cleanup

* add test skip for when compressed tensors is not installed

* remove pydantic import + style

* delay torch import in test

* initial docs

* update main init for compressed tensors config

* make fix-copies

* docstring

* remove fill_docstring

* Apply suggestions from code review

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* review comments

* review comments

* comments - suppress warnings on state dict load, tests, fixes

* bug-fix - remove unnecessary call to apply quant lifecycle

* run_compressed compatability

* revert changes not needed for compression

* no longer need unexpected keys fn

* unexpected keys not needed either

* Apply suggestions from code review

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* add to_diff_dict

* update docs and expand testing

* Update _toctree.yml with compressed-tensors

* Update src/transformers/utils/quantization_config.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* update doc

* add note about saving a loaded model

---------

Co-authored-by: George Ohashi <george@neuralmagic.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Sara Adkins <sara@neuralmagic.com>
Co-authored-by: Sara Adkins <sara.adkins65@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
Co-authored-by: Dipika <dipikasikka1@gmail.com>
2024-09-25 14:31:38 +02:00
jiqing-feng
11c27dd331
Enable BNB multi-backend support (#31098)
* enable cpu bnb path

* fix style

* fix code style

* fix 4 bit path

* Update src/transformers/utils/import_utils.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* add multi backend refactor tests

* fix style

* tweak 4bit quantizer + fix corresponding tests

* tweak 8bit quantizer + *try* fixing corresponding tests

* fix dequant bnb 8bit

* account for Intel CPU in variability of expected outputs

* enable cpu and xpu device map

* further tweaks to account for Intel CPU

* fix autocast to work with both cpu + cuda

* fix comments

* fix comments

* switch to testing_utils.torch_device

* allow for xpu in multi-gpu tests

* fix tests 4bit for CPU NF4

* fix bug with is_torch_xpu_available needing to be called as func

* avoid issue where test reports attr err due to other failure

* fix formatting

* fix typo from resolving of merge conflict

* polish based on last PR review

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* fix CI

* Update src/transformers/integrations/integration_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/integrations/integration_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fix error log

* fix error msg

* add \n in error log

* make quality

* rm bnb cuda restriction in doc

* cpu model don't need dispatch

* fix doc

* fix style

* check cuda avaliable in testing

* fix tests

* Update docs/source/en/model_doc/chameleon.md

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update docs/source/en/model_doc/llava_next.md

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update tests/quantization/bnb/test_4bit.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update tests/quantization/bnb/test_4bit.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* fix doc

* fix check multibackends

* fix import sort

* remove check torch in bnb

* docs: update bitsandbytes references with multi-backend info

* docs: fix small mistakes in bnb paragraph

* run formatting

* reveret bnb check

* move bnb multi-backend check to import_utils

* Update src/transformers/utils/import_utils.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* fix bnb check

* minor fix for bnb

* check lib first

* fix code style

* Revert "run formatting"

This reverts commit ac108c6d6b.

* fix format

* give warning when bnb version is low and no cuda found]

* fix device assignment check to be multi-device capable

* address akx feedback on get_avlbl_dev fn

* revert partially, as we don't want the function that public, as docs would be too much (enforced)

---------

Co-authored-by: Aarni Koskela <akx@iki.fi>
Co-authored-by: Titus von Koeller <9048635+Titus-von-Koeller@users.noreply.github.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2024-09-24 03:40:56 -06:00
Theia Vogel
e719b65c31
Fix FbgemmFp8Linear not preserving tensor shape (#33239)
* add tests for linear shape behavior

* fix linear shape behavior

ended up adding the reshape at the end, after f8f8bf16_rowwise, because adding
it directly after quantize_fp8_per_row caused f8f8bf16_rowwise to drop the
seq_len dimension. (i.e., (17, 23, 1014) -> (17, 1024))

* save shape up front + comment
2024-09-11 13:26:44 +02:00
Alazar
96429e74a8
Add support for GGUF Phi-3 (#31844)
* Update docs for GGUF supported models

* Add tensor mappings and define class GGUFPhi3Converter

* Fix tokenizer

* Working version

* Attempt to fix some CI failures

* Run ruff format

* Add vocab, merges, decoder methods like LlamaConverter

* Resolve conflicts since Qwen2Moe was added to gguf

- I missed one place when resolving conflict
- I also made a mistake with tests_ggml.py and now has been fixed to reflect
its master version.
2024-09-10 13:32:38 +02:00
Vladislav Bronzov
5d11de4a2f
Add Qwen2Moe GGUF loading support (#33264)
* update gguf doc, config and tensor mapping

* add qwen2moe architecture support, GGUFQwen2MoeConverter and q4 unit tests

* apply code style fixes

* reformat files

* assign GGUFQwen2Converter to qwen2_moe
2024-09-05 17:42:03 +02:00
Isotr0py
edeca4387c
🚨 Support dequantization for most GGML types (#32625)
* use gguf internal dequantize

* add Q5_0 test

* add iq1 test

* add remained test

* remove duplicated test

* update docs

* add gguf version limit

* make style

* update gguf import catch

* revert vocab_size patch

* make style

* use GGUF_MIN_VERSION everywhere
2024-09-03 12:58:14 +02:00
Marc Sun
9ea1eacd11
remove to restriction for 4-bit model (#33122)
* remove to restiction for 4-bit model

* Update src/transformers/modeling_utils.py

Co-authored-by: Matthew Douglas <38992547+matthewdouglas@users.noreply.github.com>

* bitsandbytes: prevent dtype casting while allowing device movement with .to or .cuda

* quality fix

* Improve warning message for .to() and .cuda() on bnb quantized models

---------

Co-authored-by: Matthew Douglas <38992547+matthewdouglas@users.noreply.github.com>
2024-09-02 16:28:50 +02:00
Joao Gante
cf32ee1753
Cache: use batch_size instead of max_batch_size (#32657)
* more precise name

* better docstrings

* Update src/transformers/cache_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2024-08-16 11:48:45 +01:00
Jerry Zhang
78d78cdf8a
Add TorchAOHfQuantizer (#32306)
* Add TorchAOHfQuantizer

Summary:
Enable loading torchao quantized model in huggingface.

Test Plan:
local test

Reviewers:

Subscribers:

Tasks:

Tags:

* Fix a few issues

* style

* Added tests and addressed some comments about dtype conversion

* fix torch_dtype warning message

* fix tests

* style

* TorchAOConfig -> TorchAoConfig

* enable offload + fix memory with multi-gpu

* update torchao version requirement to 0.4.0

* better comments

* add torch.compile to torchao README, add perf number link

---------

Co-authored-by: Marc Sun <marc@huggingface.co>
2024-08-14 16:14:24 +02:00
Penut Chen
1c122a46dc
Support dequantizing GGUF FP16 format (#31783)
* support gguf fp16

* support gguf bf16 with pytorch

* add gguf f16 test

* remove bf16
2024-07-24 17:59:59 +02:00
Ita Zaporozhets
a1844a3209
gguf conversion add_prefix_space=None for llama3 (#31937)
* gguf conversion forces add_prefix_space=False for llama3, this is not required and forces from_slow, which fails. changing to None + test

* typo

* clean test
2024-07-23 11:45:54 +02:00
Marc Sun
96a074fa7e
Add new quant method (#32047)
* Add new quant method

* update

* fix multi-device

* add test

* add offload

* style

* style

* add simple example

* initial doc

* docstring

* style again

* works ?

* better docs

* switch to non persistant

* remove print

* fix init

* code review
2024-07-22 20:21:59 +02:00
Penut Chen
ac946aac25
Fix the incorrect permutation of gguf (#31788)
* Fix the incorrect permutation of gguf

* rename num_kv_heads

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* add typing to num_kv_heads

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* rename variables

* refactor permute function name

* update the expected text of the llama3 q4 test

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
2024-07-16 08:20:34 +02:00
amyeroberts
1de7dc7403
Skip tests properly (#31308)
* Skip tests properly

* [test_all]

* Add 'reason' as kwarg for skipTest

* [test_all] Fix up

* [test_all]
2024-06-26 21:59:08 +01:00
Younes Belkada
6d4306160a
GGUF: Fix llama 3 GGUF (#31358)
* Create push-important-models.yml

* llama3 support for GGUF

* fixup

* Update src/transformers/integrations/ggml.py

* fix pre-tokenizer

* fix

* fix

* fix

* fix

* fix

* fix

* address final comment

* handle special tokens + add tests
2024-06-20 14:29:58 +02:00
Ella Charlaix
02300273e2
🚨 Remove dataset with restrictive license (#31452)
remove dataset with restrictive license
2024-06-17 17:56:51 +01:00
Albert Villanova del Moral
a14b055b65
Pass datasets trust_remote_code (#31406)
* Pass datasets trust_remote_code

* Pass trust_remote_code in more tests

* Add trust_remote_dataset_code arg to some tests

* Revert "Temporarily pin datasets upper version to fix CI"

This reverts commit b7672826ca.

* Pass trust_remote_code in librispeech_asr_dummy docstrings

* Revert "Pin datasets<2.20.0 for examples"

This reverts commit 833fc17a3e.

* Pass trust_remote_code to all examples

* Revert "Add trust_remote_dataset_code arg to some tests" to research_projects

* Pass trust_remote_code to tests

* Pass trust_remote_code to docstrings

* Fix flax examples tests requirements

* Pass trust_remote_dataset_code arg to tests

* Replace trust_remote_dataset_code with trust_remote_code in one example

* Fix duplicate trust_remote_code

* Replace args.trust_remote_dataset_code with args.trust_remote_code

* Replace trust_remote_dataset_code with trust_remote_code in parser

* Replace trust_remote_dataset_code with trust_remote_code in dataclasses

* Replace trust_remote_dataset_code with trust_remote_code arg
2024-06-17 17:29:13 +01:00
Isotr0py
e4628434d8
Add Qwen2 GGUF loading support (#31175)
* add qwen2 gguf support

* Update docs

* fix qwen2 tokenizer

* add qwen2 gguf test

* fix typo in qwen2 gguf test

* format code

* Remove mistral, clarify the error message

* format code

* add typing and update docstring
2024-06-03 14:55:10 +01:00
Marc Sun
48cada87c3
Fix quantized cache output (#31143) 2024-05-31 12:08:55 +02:00
Younes Belkada
5e5c4d629d
FIX / Quantization: Add extra validation for bnb config (#31135)
add validation for bnb config
2024-05-30 11:45:03 +02:00
Marc Sun
b84cd67526
Fix quanto tests (#31062)
fix quanto tests
2024-05-27 15:53:45 +02:00
Younes Belkada
658b849aeb
Quantization / TST: Fix remaining quantization tests (#31000)
* Fix remaining quant tests

* Update test_quanto.py
2024-05-24 14:35:59 +02:00
Marc Sun
ae87f9797b
FIX / TST: Fix expected results on Mistral AWQ test (#30971)
fix awq mistral test
2024-05-24 14:06:31 +02:00
Raushan Turganbay
d583f1317b
Quantized KV Cache (#30483)
* clean-up

* Update src/transformers/cache_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/cache_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/cache_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fixup

* Update tests/quantization/quanto_integration/test_quanto.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* Update src/transformers/generation/configuration_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* more suggestions

* mapping if torch available

* run tests & add 'support_quantized' flag

* fix jamba test

* revert, will be fixed by another PR

* codestyle

* HQQ and versatile cache classes

* final update

* typo

* make tests happy

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
2024-05-23 17:25:20 +05:00
Younes Belkada
3f435823e0
FEAT / Bitsandbytes: Add dequantize API for bitsandbytes quantized models (#30806)
* add  method

* change method name

* more comments

* Apply suggestions from code review

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* fixup

* add docstrings and fix comment

* warn users on the de-quantized dtype

* Update src/transformers/quantizers/base.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/bitsandbytes.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* final suggestion - use private method

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-05-15 17:17:09 +02:00
Lysandre Debut
a42844955f
Loading GGUF files support (#30391)
* Adds support for loading GGUF files

Co-authored-by: Younes Belkada <younesbelkada@gmail.com>
Co-authored-by: 99991 <99991@users.noreply.github.com>

* add q2_k q3_k q5_k support from @99991

* fix tests

* Update doc

* Style

* Docs

* fix CI

* Update docs/source/en/gguf.md

* Update docs/source/en/gguf.md

* Compute merges

* change logic

* add comment for clarity

* add comment for clarity

* Update src/transformers/models/auto/tokenization_auto.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* change logic

* Update src/transformers/modeling_utils.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* change

* Apply suggestions from code review

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/modeling_gguf_pytorch_utils.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* put back comment

* add comment about mistral

* comments and added tests

* fix unconsistent type

* more

* fix tokenizer

* Update src/transformers/modeling_utils.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* address comments about tests and tokenizer + add added_tokens

* from_gguf -> gguf_file

* replace on docs too

---------

Co-authored-by: Younes Belkada <younesbelkada@gmail.com>
Co-authored-by: 99991 <99991@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-05-15 14:28:20 +02:00
Marc Sun
de6e0db184
[awq] replace scale when we have GELU (#30074)
* fix awq test

* style

* add log

* new fix

* style

* only modifying impacted model in the end

* rename function
2024-05-13 11:41:03 +02:00
Younes Belkada
9c772ac888
Quantization / HQQ: Fix HQQ tests on our runner (#30668)
Update test_hqq.py
2024-05-06 11:33:52 +02:00
mobicham
59952994c4
Add HQQ quantization support (#29637)
* update HQQ transformers integration

* push import_utils.py

* add force_hooks check in modeling_utils.py

* fix | with Optional

* force bias as param

* check bias is Tensor

* force forward for multi-gpu

* review fixes pass

* remove torch grad()

* if any key in linear_tags fix

* add cpu/disk check

* isinstance return

* add multigpu test + refactor tests

* clean hqq_utils imports in hqq.py

* clean hqq_utils imports in quantizer_hqq.py

* delete hqq_utils.py

* Delete src/transformers/utils/hqq_utils.py

* ruff init

* remove torch.float16 from __init__ in test

* refactor test

* isinstance -> type in quantizer_hqq.py

* cpu/disk device_map check in quantizer_hqq.py

* remove type(module) nn.linear check in quantizer_hqq.py

* add BaseQuantizeConfig import inside HqqConfig init

* remove hqq import in hqq.py

* remove accelerate import from test_hqq.py

* quant config.py doc update

* add hqqconfig to main_classes doc

* make style

* __init__ fix

* ruff __init__

* skip_modules list

* hqqconfig format fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* hqqconfig doc fix

* test_hqq.py remove mistral comment

* remove self.using_multi_gpu is False

* torch_dtype default val set and logger.info

* hqq.py isinstance fix

* remove torch=None

* torch_device test_hqq

* rename test_hqq

* MODEL_ID in test_hqq

* quantizer_hqq setattr fix

* quantizer_hqq typo fix

* imports quantizer_hqq.py

* isinstance quantizer_hqq

* hqq_layer.bias reformat quantizer_hqq

* Step 2 as comment in quantizer_hqq

* prepare_for_hqq_linear() comment

* keep_in_fp32_modules fix

* HqqHfQuantizer reformat

* quantization.md hqqconfig

* quantization.md model example reformat

* quantization.md # space

* quantization.md space   })

* quantization.md space   })

* quantization_config fix doc

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* axis value check in quantization_config

* format

* dynamic config explanation

* quant config method in quantization.md

* remove shard-level progress

* .cuda fix modeling_utils

* test_hqq fixes

* make fix-copies

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-05-02 17:51:49 +01:00
Joao Gante
75bbfd5b22
Cache: Static cache as a standalone object (#30476) 2024-04-30 16:37:19 +01:00
zhong zhuang
b4c18a830a
[FEAT]: EETQ quantizer support (#30262)
* [FEAT]: EETQ quantizer support

* Update quantization.md

* Update docs/source/en/main_classes/quantization.md

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update docs/source/en/quantization.md

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update docs/source/en/quantization.md

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/__init__.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/__init__.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update tests/quantization/eetq_integration/test_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/quantizers/auto.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/quantizers/auto.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/quantizers/auto.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/quantizers/quantizer_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update tests/quantization/eetq_integration/test_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/quantizers/quantizer_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update tests/quantization/eetq_integration/test_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update tests/quantization/eetq_integration/test_eetq.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* [FEAT]: EETQ quantizer support

* [FEAT]: EETQ quantizer support

* remove whitespaces

* update quantization.md

* style

* Update docs/source/en/quantization.md

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* add copyright

* Update quantization.md

* Update docs/source/en/quantization.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update docs/source/en/quantization.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Address the comments by amyeroberts

* style

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Marc Sun <marc@huggingface.co>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-04-22 20:38:58 +01:00
Younes Belkada
080b700805
FIX / AWQ: Fix failing exllama test (#30288)
fix filing exllama test
2024-04-17 11:26:35 +02:00
Marc Sun
58a939c6b7
Fix quantization tests (#29914)
* revert back to torch 2.1.1

* run test

* switch to torch 2.2.1

* udapte dockerfile

* fix awq tests

* fix test

* run quanto tests

* update tests

* split quantization tests

* fix

* fix again

* final fix

* fix report artifact

* build docker again

* Revert "build docker again"

This reverts commit 399a5f9d93.

* debug

* revert

* style

* new notification system

* testing notfication

* rebuild docker

* fix_prev_ci_results

* typo

* remove warning

* fix typo

* fix artifact name

* debug

* issue fixed

* debug again

* fix

* fix time

* test notif with faling test

* typo

* issues again

* final fix ?

* run all quantization tests again

* remove name to clear space

* revert modfiication done on workflow

* fix

* build docker

* build only quant docker

* fix quantization ci

* fix

* fix report

* better quantization_matrix

* add print

* revert to the basic one
2024-04-09 17:10:29 +02:00
Marc Sun
4207a4076d
[bnb] Fix offload test (#30039)
fix bnb test
2024-04-05 13:11:28 +02:00
Marc Sun
28de2f4de3
[Quantization] Quanto quantizer (#29023)
* start integration

* fix

* add and debug tests

* update tests

* make pytorch serialization works

* compatible with device_map and offload

* fix tests

* make style

* add ref

* guard against safetensors

* add float8 and style

* fix is_serializable

* Fix shard_checkpoint compatibility with quanto

* more tests

* docs

* adjust memory

* better

* style

* pass tests

* Update src/transformers/modeling_utils.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* add is_safe_serialization instead

* Update src/transformers/quantizers/quantizer_quanto.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* add QbitsTensor tests

* fix tests

* simplify activation list

* Update docs/source/en/quantization.md

Co-authored-by: David Corvoysier <david.corvoysier@gmail.com>

* better comment

* Update tests/quantization/quanto_integration/test_quanto.py

Co-authored-by: David Corvoysier <david.corvoysier@gmail.com>

* Update tests/quantization/quanto_integration/test_quanto.py

Co-authored-by: David Corvoysier <david.corvoysier@gmail.com>

* find and fix edge case

* Update docs/source/en/quantization.md

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* pass weights_only_kwarg instead

* fix shard_checkpoint loading

* simplify update_missing_keys

* Update tests/quantization/quanto_integration/test_quanto.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* recursion to get all tensors

* block serialization

* skip serialization tests

* fix

* change by cuda:0 for now

* fix regression

* update device_map

* fix doc

* add noteboon

* update torch_dtype

* update doc

* typo

* typo

* remove comm

---------

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: David Corvoysier <david.corvoysier@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Younes Belkada <younesbelkada@gmail.com>
2024-03-15 11:51:29 -04:00
Ilyas Moutawwakil
4fc708f98c
Exllama kernels support for AWQ models (#28634)
* added exllama kernels support for awq models

* doc

* style

* Update src/transformers/modeling_utils.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* refactor

* moved exllama post init to after device dispatching

* bump autoawq version

* added exllama test

* style

* configurable exllama kernels

* copy exllama_config from gptq

* moved exllama version check to post init

* moved to quantization dockerfile

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
2024-03-05 03:22:48 +01:00
Andrei Panferov
e3fc90ae68
Cleaner Cache dtype and device extraction for CUDA graph generation for quantizers compatibility (#29079)
* input_layernorm as the beacon of hope

* cleaner dtype extraction

* AQLM + CUDA graph test

* is available check

* shorter text test
2024-02-27 09:32:39 +01:00
Younes Belkada
ff76e7c212
FIX [bnb / tests] Propagate the changes from #29092 to 4-bit tests (#29122)
* forgot to push the changes for 4bit ..

* trigger CI
2024-02-20 11:11:15 +01:00