ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
2,811 commits 391 branches 58 tags 304 MiB
Commit graph

2,811 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
4cedbf55bb Update rl.py 2025-09-16 06:20:06 -07:00
pluesclues
96c2ecb648
 		TRL Updated version of VLM GRPO update along with GSPO (#3132) 
* Kept, padding logic

* Made sure prediction step in rl.py allows logging for callbacks in RL trainers

* updated llama.py to new online_dpo changes

* Update rl.py to make logic simpiler

* Update rl.py, made sure tokenized_output on eval step was on same device

* Update rl.py, corrected tokenized_outputs to inputs

* Update rl.py, removed sagemaker stuff

* Update llama.py, figures out if there is right padding automatically

* Update llama.py, changed conditional statement for right padding slightlyt

* Update llama.py, updated OS.environ variable to temp variable

* Update rl.py, made it account for right padding in online dpo and reward modeling

* Update llama.py, automatically figures out if right padding is needed

* Update rl_replacements.py, fixed up passing image data to functions

* Update rl_replacements.py, for VLM GRPO support with TRL

* Update rl_replacements.py, gspo added

* Update rl.py, forgot about Online_DPO changes in this branch

* Update rl.py, forgot to not include Online DPO PR changes

* Update llama.py, forgot to disinclude Online DPO PR changes

* Update rl_replacements.py, updated generate and score completions to be up to date for trl

* Update rl_replacements.py

* Update rl_replacements.py, fixed nan issues with vlms

* Update rl_replacements.py, added indent

* Update rl_replacements.py, added attention mask to calculations of old and ref hidden states

* Update unsloth/models/rl_replacements.py

* Update unsloth/models/rl_replacements.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-09-16 05:43:07 -07:00
Datta Nimmaturi
a6176ad4fe
 		Fast Inference with vLLM for VLMs (#2975) 
* [WIP] use vLLM for vision language models

* Update README.md

Editing icon sizes

* Update README.md

Updating icon sizes

* Update README.md (#2885)

* MoE kernels AGPLv3

* versioning

* Many bug fixes (#2908)

* add deepseek v3

* add deepseek r1 base

* add deepseek r1 zero

* add deepseek distill llama

* add deepseek distill models

* remove redundant code when constructing model names

* add mistral small to registry

* rename model registration methods

* rename deepseek registration methods

* refactor naming for mistral and phi

* add global register models

* refactor model registration tests for new registry apis

* add model search method

* remove deprecated registration api

* add quant type test

* add registry readme

* make llama registration more specific

* clear registry when executing individual model registration file

* more registry readme updates

* Update _auto_install.py

* Llama4

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Synthetic data

* Update mapper.py

* Xet and Synthetic

* Update synthetic.py

* Update loader.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update pyproject.toml

* Delete .gitignore

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update _utils.py

* Update pyproject.toml

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update chat_templates.py

* Seasame force float16 / float32

* Fix Seasame

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* is_multimodal

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* UNSLOTH_DISABLE_STATIC_GENERATION

* Update vision.py

* Auto vision detection

* Sesame

* Whisper

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* logging

* Update pyproject.toml

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* logits / temperature

* Update rl_replacements.py

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Debugging only

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Generic efficient GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* Remove debugging

* Update rl_replacements.py

* Update rl_replacements.py

* Update vision.py

* Update llama.py

* Update rl_replacements.py

* versioning

* Update _utils.py

* Update vision.py

* Update mapper.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update loader.py

* Update _utils.py

* Update vision.py

* gradient checkpointing

* Gemma 3N fixes

* Update loader.py

* Versioning

* Gemma 3N fixes

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Fix setup.py

* setup.py

* Prints

* Update setup.py

* Update setup.py

* Update setup.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update vision.py

* Update vision.py

* Update pyproject.toml

* Update vision.py

* Update _utils.py

* Update __init__.py

* Update __init__.py

---------

Co-authored-by: jeromeku <jerome.ku@gmail.com>
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>

* silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912)

* Dynamically adjust get_per_token_logps function and patch as well (#2911)

* add intel gpu with vllm support (#2903)

* [bugs] fix for casual mask (#2868)

* fix for casual mask

* use un_casual in sdpa

* add missing mask

* fix for type

* Explicitly check if xformers exists for attention (#2889)

* Update __init__.py

* Update llama.py

* if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913)

* Move inputs to right devices. (#2919)

* Move tensors to right devices

* fix multi gpu for non mistral models

* multi GPU RoPE for gemma2

* Finish up multi GPU inference

* Make multiGPU rope a list

* Remove unnecessary transfer to CPU

* Remove unnecessary move to CPU

* Donot move inputs to device yet

will be handled separately in another PR

* Move inputs to appropriate decoder device

* Make device count global variable

* Cleanup RoPE device code

* Fixup num_gpu to device count

* Cleanup device counts

* Use device index for RoPE get_cache

* Donot typecast

* Use tuple instead of list for tensors. Use device index directly

* fixup move to device logic

* WIP VLM vLLM

* Make vLLM patch a function

* Add save and load lora functions

* Make fast_inference setup depend on the flag

* Improve fast inference patching mechanism

* Make vision setting depend on checks in fastbasemodel

* Check LoRA and vLLM intercompatibility for vision models

* Comment pointing to vLLM LoRA check

* Improve lora validation on vLLM

* Error out on no vLLM and increase max lora rank

* Bug fixes (#3017)

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update pyproject.toml

* Delete .gitignore

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update _utils.py

* Update pyproject.toml

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update chat_templates.py

* Seasame force float16 / float32

* Fix Seasame

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* is_multimodal

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* UNSLOTH_DISABLE_STATIC_GENERATION

* Update vision.py

* Auto vision detection

* Sesame

* Whisper

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* logging

* Update pyproject.toml

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* logits / temperature

* Update rl_replacements.py

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Debugging only

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Generic efficient GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* Remove debugging

* Update rl_replacements.py

* Update rl_replacements.py

* Update vision.py

* Update llama.py

* Update rl_replacements.py

* versioning

* Update _utils.py

* Update vision.py

* Update mapper.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update loader.py

* Update _utils.py

* Update vision.py

* gradient checkpointing

* Gemma 3N fixes

* Update loader.py

* Versioning

* Gemma 3N fixes

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Fix setup.py

* setup.py

* Prints

* Update setup.py

* Update setup.py

* Update setup.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update vision.py

* Update vision.py

* Update pyproject.toml

* Update vision.py

* Update _utils.py

* Update __init__.py

* Update __init__.py

* Small fixes

* Update vision.py

* Update vision.py

* versioning

* Update __init__.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update vision.py

* Update vision.py

* compiler stance

* Update _utils.py

* Update pyproject.toml

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990)

This reverts commit 204fc46e19.

* skip_guard_eval_unsafe fix

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update llama.py

* Update llama.py

* Fix `quantization_method`

* versioning

* fix for casual mask (#3011)

* [intel] add for intel path for llama.py (#3012)

* fix for intel path

* remove unuse code

* Update unsloth/models/llama.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update llama.py

* Fix Gemma 2 (#3024)

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update pyproject.toml

* Delete .gitignore

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update _utils.py

* Update pyproject.toml

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update chat_templates.py

* Seasame force float16 / float32

* Fix Seasame

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* is_multimodal

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* UNSLOTH_DISABLE_STATIC_GENERATION

* Update vision.py

* Auto vision detection

* Sesame

* Whisper

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* logging

* Update pyproject.toml

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* logits / temperature

* Update rl_replacements.py

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Debugging only

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Generic efficient GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* Remove debugging

* Update rl_replacements.py

* Update rl_replacements.py

* Update vision.py

* Update llama.py

* Update rl_replacements.py

* versioning

* Update _utils.py

* Update vision.py

* Update mapper.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update loader.py

* Update _utils.py

* Update vision.py

* gradient checkpointing

* Gemma 3N fixes

* Update loader.py

* Versioning

* Gemma 3N fixes

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Fix setup.py

* setup.py

* Prints

* Update setup.py

* Update setup.py

* Update setup.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update vision.py

* Update vision.py

* Update pyproject.toml

* Update vision.py

* Update _utils.py

* Update __init__.py

* Update __init__.py

* Small fixes

* Update vision.py

* Update vision.py

* versioning

* Update __init__.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update vision.py

* Update vision.py

* compiler stance

* Update _utils.py

* Update pyproject.toml

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990)

This reverts commit 204fc46e19.

* skip_guard_eval_unsafe fix

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update llama.py

* Update llama.py

* Fix `quantization_method`

* versioning

* Update _utils.py

* Update _utils.py

* Update _utils.py

* falcon force float32 on sm<75 machines (#3026)

* Fix torch compile issues (#3028)

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update pyproject.toml

* Delete .gitignore

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update _utils.py

* Update pyproject.toml

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update chat_templates.py

* Seasame force float16 / float32

* Fix Seasame

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* is_multimodal

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* UNSLOTH_DISABLE_STATIC_GENERATION

* Update vision.py

* Auto vision detection

* Sesame

* Whisper

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* logging

* Update pyproject.toml

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* logits / temperature

* Update rl_replacements.py

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Debugging only

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Generic efficient GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* Remove debugging

* Update rl_replacements.py

* Update rl_replacements.py

* Update vision.py

* Update llama.py

* Update rl_replacements.py

* versioning

* Update _utils.py

* Update vision.py

* Update mapper.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update loader.py

* Update _utils.py

* Update vision.py

* gradient checkpointing

* Gemma 3N fixes

* Update loader.py

* Versioning

* Gemma 3N fixes

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Fix setup.py

* setup.py

* Prints

* Update setup.py

* Update setup.py

* Update setup.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update vision.py

* Update vision.py

* Update pyproject.toml

* Update vision.py

* Update _utils.py

* Update __init__.py

* Update __init__.py

* Small fixes

* Update vision.py

* Update vision.py

* versioning

* Update __init__.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update vision.py

* Update vision.py

* compiler stance

* Update _utils.py

* Update pyproject.toml

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990)

This reverts commit 204fc46e19.

* skip_guard_eval_unsafe fix

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update llama.py

* Update llama.py

* Fix `quantization_method`

* versioning

* Update _utils.py

* Update _utils.py

* Update _utils.py

* check stride

* Cleanup

* Update rope_embedding.py

* Update gemma2.py

* Fix `set_stance`

* Update pyproject.toml

* Update _utils.py

* Fixup patch vllm

* Disable mllama

* Use variables to decide VLM support

* Better attn_impl handling

* Patch TF protobuf incompatability

* Torch 2.8 (#3186)

* Fix mamba

* Update loader.py

* Update vision.py

* Update loader.py

* Filter vLLM standby logs (#3131)

* filter vLLM standby logs

* safeguard standby logger patch

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update loader.py

* Add scaler

* Update llama.py

* Update _utils.py

* Versioning

* GPT OSS fix

* GPT OSS fix

* Update loader.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Versioning

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Upcast norms

* Update loader.py

* Update vision.py

* Upcast layernorms

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Update rl.py

* Update pyproject.toml

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Torch 2.8

* Update rl_replacements.py

---------

Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>

* Update _auto_install.py

* Update pyproject.toml

* Update rl.py

* Protobuf issue

* Update pyproject.toml

* Fix extras transformers typo in pyproject.toml

* Update _utils.py

* Bug fixes (#3195)

* Fix mamba

* Update loader.py

* Update vision.py

* Update loader.py

* Filter vLLM standby logs (#3131)

* filter vLLM standby logs

* safeguard standby logger patch

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update loader.py

* Add scaler

* Update llama.py

* Update _utils.py

* Versioning

* GPT OSS fix

* GPT OSS fix

* Update loader.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Versioning

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Upcast norms

* Update loader.py

* Update vision.py

* Upcast layernorms

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Update rl.py

* Update pyproject.toml

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Torch 2.8

* Update rl_replacements.py

* Update loader.py

* UNSLOTH_ENABLE_CCE

* Fix

* Update loader.py

* Update loader.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Import fixes

* Update loader.py

* Fix aimv2 issue

* Update loader.py

* Update import_fixes.py

* Update import_fixes.py

* Update loader.py

* Update loader.py

* Update loader.py

* Upgrade

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

---------

Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>

* adallow float32 dtype in FastLanguageModel (#3204)

* Update loader.py

* Update vision.py

* Suppress message and use unsloth sampling params

* Use trl sampling params for now

* Improve error message

* fixup quantized fast inference model name

---------

Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: jeromeku <jerome.ku@gmail.com>
Co-authored-by: DoubleMathew <mmathew23@gmail.com>
Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com>
Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
 2025-09-16 05:29:08 -07:00
lightsource
3808d801a7
 		Add support for modules_to_save in FastModel.get_peft_model (#3317) 
* patch modules_to_save

* Update vision.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-09-15 22:41:34 -07:00
Daniel Han
4af624557f
 		Bug fixes (#3322) 
* Fix mamba

* Update loader.py

* Update vision.py

* Update loader.py

* Filter vLLM standby logs (#3131)

* filter vLLM standby logs

* safeguard standby logger patch

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update loader.py

* Add scaler

* Update llama.py

* Update _utils.py

* Versioning

* GPT OSS fix

* GPT OSS fix

* Update loader.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Versioning

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Upcast norms

* Update loader.py

* Update vision.py

* Upcast layernorms

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Update rl.py

* Update pyproject.toml

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Torch 2.8

* Update rl_replacements.py

* Update loader.py

* UNSLOTH_ENABLE_CCE

* Fix

* Update loader.py

* Update loader.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Import fixes

* Update loader.py

* Fix aimv2 issue

* Update loader.py

* Update import_fixes.py

* Update import_fixes.py

* Update loader.py

* Update loader.py

* Update loader.py

* Upgrade

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* custom_datatype

* recheck

* Float16

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Bug fix

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* torch_dtype

* Update rl.py

* Fix CE Loss

* Versioning

* Update loader.py

* Update loader.py

* extract_model_type_from_config

* Model types

* Update loader.py

* get_transformers_model_type

* Update loader.py

* Update loader.py

* Update loader.py

* Update rl.py

* Update pyproject.toml

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Versioning

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

---------

Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>
 2025-09-15 01:55:24 -07:00
Daniel Han
e204e93599 Update README.md 2025-09-15 01:46:07 -07:00
Daniel Han
1d83c5ffe8 Update README.md 2025-09-15 01:43:11 -07:00
Daniel Han
fdbee04f96 Update README.md 2025-09-15 01:42:59 -07:00
Daniel Han
e66427f795 Update README.md 2025-09-15 01:40:28 -07:00
Daniel Han
a40ccf8d33 Update README.md 2025-09-15 01:40:06 -07:00
Daniel Han
fe291a10a9 Update README.md 2025-09-15 01:39:39 -07:00
Daniel Han
b73e9b0b9e Blackwell support 2025-09-15 01:39:03 -07:00
Michael Han
c7fc68c5e0
 		Update README.md 2025-09-13 21:45:22 -07:00
Michael Han
dbaff8a0dd
 		Update README.md 
Adding new install instructions
 2025-09-13 21:30:52 -07:00
Daniel Han
e025ca9013 importlib_version 2025-09-12 03:13:15 -07:00
billishyahao
c07f1ec903
 		[ROCm] add hip device path (#3301) 2025-09-12 02:57:19 -07:00
Daniel Han
f06200db07 Bug fix 2025-09-10 05:14:15 -07:00
Daniel Han
5b5e034805 Update rl.py 2025-09-10 01:39:35 -07:00
Daniel Han
1afedc81ee
 		Bug fixes (#3295) 
* Fix mamba

* Update loader.py

* Update vision.py

* Update loader.py

* Filter vLLM standby logs (#3131)

* filter vLLM standby logs

* safeguard standby logger patch

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update loader.py

* Add scaler

* Update llama.py

* Update _utils.py

* Versioning

* GPT OSS fix

* GPT OSS fix

* Update loader.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Versioning

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Upcast norms

* Update loader.py

* Update vision.py

* Upcast layernorms

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Update rl.py

* Update pyproject.toml

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Torch 2.8

* Update rl_replacements.py

* Update loader.py

* UNSLOTH_ENABLE_CCE

* Fix

* Update loader.py

* Update loader.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Import fixes

* Update loader.py

* Fix aimv2 issue

* Update loader.py

* Update import_fixes.py

* Update import_fixes.py

* Update loader.py

* Update loader.py

* Update loader.py

* Upgrade

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* custom_datatype

* recheck

* Float16

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Bug fix

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* torch_dtype

* Update rl.py

* Fix CE Loss

* Versioning

* Update loader.py

* Update loader.py

* extract_model_type_from_config

* Model types

* Update loader.py

* get_transformers_model_type

* Update loader.py

* Update loader.py

* Update loader.py

* Update rl.py

* Update pyproject.toml

* Update loader.py

---------

Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>
 2025-09-10 01:28:13 -07:00
Daniel Han
def96ca486 Update loader.py 2025-09-09 02:06:07 -07:00
Daniel Han
33c2bd031c Merge branch 'main' of https://github.com/unslothai/unsloth 2025-09-09 01:22:27 -07:00
DoubleMathew
a5968f30b2
 		simplify uns inference (#3291) 2025-09-08 21:07:02 -07:00
Daniel Han
d64e5710fa Merge branch 'main' of https://github.com/unslothai/unsloth 2025-09-08 17:15:57 -07:00
Daniel Han
379bc57b7b Update __init__.py 2025-09-08 17:15:55 -07:00
andrewor14
3541f6e8d0
 		Add support for QAT full fine-tuning (#3238) 
**Summary:** Following https://github.com/unslothai/unsloth/pull/2976,
which adds support for QAT + LoRA, this PR adds support for QAT
during full fine-tuning. See the [torchao QAT README](https://github.com/pytorch/ao/blob/main/torchao/quantization/qat/README.md)
for more details.

Current QAT schemes supported are:
```
fp8-int4, targeting the torch.ops.fbgemm.f8i4bf16_shuffled kernel
fp8-fp8, targeting the torch.ops.fbgemm.f8f8bf16_rowwise kernel
```

**Test Plan:** https://gist.github.com/andrewor14/048b5c1bd01b7fa23c53913856a8ef9f

Full fine-tuning Llama3.1-8B with and without QAT on `yahma/alpaca-cleaned` for 1 epoch:
- Batch size = 16 (no grad accum)
- Learning rate = 4e-5
- Quantization scheme = fp8-int4

Wikitext perplexity:
- QAT improved perplexity by 19.2% compared to regular fine-tuning
- QAT's int4 quantized model even outperformed the bf16 baseline
- Regular int4 quantized model (without QAT) was significantly worse than the bf16 baseline

```
==> unsloth_model_full_baseline_output/eval_float.log <==
|        |       |none  |     0|word_perplexity|↓  |9.8446|±  |   N/A|

==> unsloth_model_full_baseline_output/eval_quantized.log <==
|        |       |none  |     0|word_perplexity|↓  |11.4595|±  |   N/A|

==> unsloth_model_full_qat_fp8-int4_output/eval_quantized.log <==
|        |       |none  |     0|word_perplexity|↓  |9.2336|±  |   N/A|
```

Fibonacci test:
- Both bf16 baseline and int4 quantized models correctly identified 13 as the next number
- QAT quantized model was more succinct in its response
- No substantial differences here

```
### Instruction:
Continue the fibonnaci sequence.

### Input:
1, 1, 2, 3, 5, 8

==> unsloth_model_full_baseline_output/eval_float.log <==
### Response:
The next number in the Fibonacci sequence is 13.<|end_of_text|>

==> unsloth_model_full_baseline_output/eval_quantized.log <==
### Response:
The next number in the Fibonacci sequence is 13.<|end_of_text|>

==> unsloth_model_full_qat_fp8-int4_output/eval_quantized.log <==
### Response:
13<|end_of_text|>
```
 2025-09-08 15:07:50 -07:00
DoubleMathew
cf9a00eba8
 		GptAttention turn training off during inference (#3289) 2025-09-08 13:47:32 -07:00
Daniel Han
cb78f0e83d Versioning 2025-09-08 06:06:04 -07:00
Daniel Han
0b6cee89fe Update __init__.py 2025-09-08 04:57:04 -07:00
Daniel Han
48f5372be0 Update __init__.py 2025-09-08 02:02:11 -07:00
Roland Tannous
551bc65235
 		Add TorchAO quantization tests with FP16 models and serialization workarounds (#3269) 
* Add TorchAO quantization tests with FP16 models and serialization workarounds

* remove unrelated files

* cleaned submission
 2025-09-04 17:22:07 -07:00
DoubleMathew
ff6cbb03d0
 		llama vision inference fix (#3270) 
* llama vision inference fix

* fix via can_compile_fullgraph instead
 2025-09-04 16:06:49 -07:00
Datta Nimmaturi
c19a002a77
 		Filter executor not sleeping log (#3268) 2025-09-04 22:05:42 +05:30
Daniel Han
978f73ed86
 		Bug fixes (#3266) 
* Fix mamba

* Update loader.py

* Update vision.py

* Update loader.py

* Filter vLLM standby logs (#3131)

* filter vLLM standby logs

* safeguard standby logger patch

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

* Update unsloth/models/_utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update loader.py

* Add scaler

* Update llama.py

* Update _utils.py

* Versioning

* GPT OSS fix

* GPT OSS fix

* Update loader.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Versioning

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Upcast norms

* Update loader.py

* Update vision.py

* Upcast layernorms

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Update rl.py

* Update pyproject.toml

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Torch 2.8

* Update rl_replacements.py

* Update loader.py

* UNSLOTH_ENABLE_CCE

* Fix

* Update loader.py

* Update loader.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Update __init__.py

* Import fixes

* Update loader.py

* Fix aimv2 issue

* Update loader.py

* Update import_fixes.py

* Update import_fixes.py

* Update loader.py

* Update loader.py

* Update loader.py

* Upgrade

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* custom_datatype

* recheck

* Float16

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Bug fix

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* torch_dtype

* Update rl.py

* Fix CE Loss

* Versioning

---------

Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>
 2025-09-04 05:17:59 -07:00
DoubleMathew
cd71b1bb96
 		disable _is_vlm (#3265) 2025-09-04 04:52:35 -07:00
Daniel Han
ffcfbe23ad Update rl.py 2025-09-04 03:25:40 -07:00
Roland Tannous
7ce3e3b2ce
 		fixed save_pretrained_torchao and associated tests (#3264) 2025-09-03 20:24:12 -07:00
Daniel Han
91b2a22548 Update import_fixes.py 2025-09-03 20:17:36 -07:00
Daniel Han
a656a3df6e Update import_fixes.py 2025-09-03 20:12:42 -07:00
Daniel Han
545f246403 Move logging 2025-09-03 20:07:27 -07:00
Daniel Han
644a2b73ec Update _utils.py 2025-09-03 20:00:21 -07:00
Daniel Han
a82d31486f Update pyproject.toml 2025-09-03 19:55:10 -07:00
Daniel Han
9f4458c57e Update llama.py 2025-09-03 19:11:53 -07:00
Jerry Zhang
5c22f06a9a
 		Support saving locally in model.save_pretrained_torchao (#3263) 
Summary:
Previously the test was not ran correctly and the save to local path is not tested
this PR added support for that and tries to test properly

Note: `python tests/saving/test_unsloth_save.py` doesn't run test

Test Plan:
pytest tests/saving/test_unsloth_save.py -k test_save_torchao

Reviewers:

Subscribers:

Tasks:

Tags:
 2025-09-03 17:51:33 -07:00
Daniel Han
10d0f25746 Update save.py 2025-09-03 15:19:02 -07:00
Lei Zhenyuan
5f14e6fcd4
 		[Intel] make intel device support ROPE (#3164) 
* make intel device pass

* abstract torch device stream
 2025-09-03 04:39:57 -07:00
stevenxdavis
12737e503d
 		Fix incorrect function call in test_qwen3_grpo.py (#3212) 
* Update test_qwen3_grpo.py to correct function call

This test file uses the incorrect name for the function, which is gradient_checkpointing_disable(), not disable_gradient_checkpointing(). 

I copied the line from test_llama32_sft.py - I'm not sure if this actually is required, just wanted it consistent for when other people like me test this and have no clue what they're doing when it throws an exception.

* Update blackwell/test_qwen3_grpo.py

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-09-03 04:39:12 -07:00
Defi Wimar
64b404877e
 		chore: Fix Typos (#3246) 2025-09-03 04:38:41 -07:00
Tim Paine
658a4703c5
 		Remove old version constraint in dependency list (#3237) 
xref: https://github.com/unslothai/unsloth-zoo/pull/258
 2025-09-01 02:29:58 -07:00
pluesclues
73dd1227b0
 		Update mistral.py, showed flag to not call cut cross entropy (#3233) 
* Update mistral.py, showed flag to not call cut cross entropy

* Update mistral.py, made it so if its not equal to zero

* Update unsloth/models/mistral.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-08-29 01:32:21 -07:00
Roland Tannous
9050d6f527
 		tests for mxfp4 and quantized models merge fix unsloth zoo pr 254 (#3223) 2025-08-29 01:30:48 -07:00