* updates
* fixup
* fix tests
* fix test
* fix
* let it be here for now, till monday
* two more fixes
* persimmon
* fixup
* fix
* fixup
* make sure fuyu runs now that LM has new attn API
* fixup + tests
* qwen vl uses new mask interface as well
* qwen image features format
* update
* remove image_sizes
* address comments
* i am dumb...
Support tensor-valued _extra_state values
TransformerEngine uses the pytorch get/set_extra_state API to store FP8
layer config information as bytes Tensor in the _extra_state entry in
the state dict. With recent changes to from_pretrained, this
functionality has broken and loading a model that uses this API doesn't
appear to work. This PR fixes the save/load pretrained functions for
extra state entries that use a pytorch tensor, and adds a (currently
x-failing) test for a dictionary extra state.
Signed-off-by: Peter St. John <pstjohn@nvidia.com>
* start refactoring whisper
* revert for now
* first step
* carry over attn fixes
* check if this works
* whisper has an off by one somewhere - cutting mask in any interface
* make it based on interface
* remove some tests that were skipped but now work
* some fixes for whisper tests
* interface changes
* change the order of fix
* some attention adjustments for eager + TP
* fix scaling
* mask changes
* why does whisper contain those extra seq lens?
* fix from config for fa2 as input_ids is invalid
* fix another test
* another fix
* disable flex attn due to compile issues
* copies and refactor for qwen audio since it somewhat relies on whisper
* fix scaling and smaller things
* retrigger
* new new interface version + more fixups
* adjust qwen
* add comment
* forgot this one
* change copies as whisper cuts on the mask
* add guard
* add flex attention
* switch to new mask function + add skips for torchscript
* remove old api with cache position
* last changes?
* trigger ci
* Firstly: Better detection of when we're a custom class
* Trigger tests
* Let's break everything
* make fixup
* fix mistaken line doubling
* Let's try to get rid of it from config classes at least
* Let's try to get rid of it from config classes at least
* Fixup image processor
* no more circular import
* Let's go back to setting `_auto_class` again
* Let's go back to setting `_auto_class` again
* stash commit
* Revert the irrelevant changes until we figure out AutoConfig
* Change tests since we're breaking expectations
* make fixup
* do the same for all custom classes
* Cleanup for feature extractor tests
* Cleanup tokenization tests too
* typo
* Fix tokenizer tests
* make fixup
* fix image processor test
* make fixup
* Remove warning from register_for_auto_class
* Stop adding model info to auto map entirely
* Remove todo
* Remove the other todo
* Let's start slapping _auto_class on models why not
* Let's start slapping _auto_class on models why not
* Make sure the tests know what's up
* Make sure the tests know what's up
* Completely remove add_model_info_to_*
* Start adding _auto_class to models
* Start adding _auto_class to models
* Add a flaky decorator
* Add a flaky decorator and import
* stash commit
* More message cleanup
* make fixup
* fix indent
* Fix trust_remote_code prompts
* make fixup
* correct indentation
* Reincorporate changes into dynamic_module_utils
* Update call to trust_remote_code
* make fixup
* Fix video processors too
* Fix video processors too
* Remove is_flaky additions
* make fixup
* use device agnostic APIs in test cases
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* fix style
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* add one more
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
* xpu now supports integer device id, aligning to CUDA behaviors
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* update to use device_properties
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* fix style
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* update comment
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* fix comments
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
* fix style
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
---------
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
* stash commit
* Experiment 1: Try just Gemma
* Experiment 1: Just try Gemma
* make fixup
* Trigger tests
* stash commit
* Try adding Gemma3 as well
* make fixup
* Correct attrib names
* Correct pipeline model mapping
* Add in all_model_classes for Gemma1 again
* Move the pipeline model mapping around again
* make fixup
* Revert Gemma3 changes since it's a VLM
* Let's try Falcon
* Correct attributes
* Correct attributes
* Let's try just overriding get_config() for now
* Do Nemotron too
* And Llama!
* Do llama/persimmon
* Correctly skip tests
* Fix Persimmon
* Include Phimoe
* Fix Gemma2
* Set model_tester_class correctly
* Add GLM
* More models!
* models models models
* make fixup
* Add Qwen3 + Qwen3MoE
* Correct import
* make fixup
* Add the QuestionAnswering classes
* Add the QuestionAnswering classes
* Move pipeline mapping to the right place
* Jetmoe too
* Stop RoPE testing models with no RoPE
* Fix up JetMOE a bit
* Fix up JetMOE a bit
* Can we just force pad_token_id all the time?
* make fixup
* fix starcoder2
* Move pipeline mapping
* Fix RoPE skipping
* Fix RecurrentGemma tests
* Fix Falcon tests
* Add MoE attributes
* Fix values for RoPE testing
* Make sure we set bos_token_id and eos_token_id in an appropriate range
* make fixup
* Fix GLM4
* Add mamba attributes
* Revert bits of JetMOE
* Re-add the JetMOE skips
* Update tests/causal_lm_tester.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Add licence
---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Get parallel loader working. Include tests.
* Update the tests for parallel loading
* Rename env variables.
* Add docs for parallel model weight loading.
* Touch up parallel model loading docs.
* Touch up parallel model loading docs again.
* Edit comment in test_modeling_utils_parallel_loading.py
* Make sure HF_PARALLEL_LOADING_WORKERS is spelled correctly in modeling_utils.py
* Correct times for parallelized loading, previous times were for a "hot" filesystem
* Update parallel model loading so the spawn method is encapsulated. DRY up the code by leveraging get_submodule.
* Update docs on model loading parallelism so that details on setting the multiprocessing start method are removed, now that the package handles this step internally.
* Fix style on model loading parallelism changes.
* Merge latest version of master's modeling_utils.
* Removed unused variable.
* Fix argument packing for the parallel loader.
* Fix state dict being undefined in the parallel model loader.
* Rename variables used in parallel model loading for clarity. Use get_module_from_name().
* Switch to the use of threads for parallel model loading.
* Update docs for parallel loading.
* Remove the use of json.loads when evaluating HF_ENABLE_PARALLEL_LOADING. Prefer simple casting.
* Move parallelized shard loading into its own function.
* Remove use of is_true(). Favor checking env var true values for HF_ENABLE_PARALLEL_LOADING.
* Update copyright to 2025 in readme for paralell model loading.
* Remove garbage collection line in load_shard_file, implicit garbage collection already occurs.
* Run formatter on modeling_utils.py
* Apply style fixes
* Delete tests/utils/test_modeling_utils_parallel_loading.py
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Cyril Vallez <cyril.vallez@huggingface.co>
* stash for now
* initial commit
* small updated
* up
* up
* works!
* nits and fixes
* don't loop too much
* finish working example
* update
* fix the small freeblocks issue
* feat: stream inputs to continuous batch
* fix: update attn from `eager` to `sdpa`
* refactor: fmt
* refactor: cleanup unnecessary code
* feat: add `update` fn to `PagedAttentionCache`
* feat: broken optimal block size computation
* fix: debugging invalid cache logic
* fix: attention mask
* refactor: use custom prompts for example
* feat: add streaming output
* fix: prefill split
refactor: add doc strings and unsound/redundant logic
fix: compute optimal blocks logic
* fix: send decoded tokens when `prefilling_split` -> `decoding`
* refactor: move logic to appropriate parent class
* fix: remove truncation as we split prefilling anyways
refactor: early return when we have enough selected requests
* feat: add paged attention forward
* push Ggraoh>
* add paged sdpa
* update
* btter mps defaults
* feat: add progress bar for `generate_batch`
* feat: add opentelemetry metrics (ttft + batch fill %age)
* feat: add tracing
* Add cuda graphs (#38059)
* draft cudagraphs addition
* nits
* styling
* update
* fix
* kinda draft of what it should look like
* fixes
* lol
* not sure why inf everywhere
* can generate but output is shit
* some fixes
* we should have a single device synch
* broken outputs but it does run
* refactor
* updates
* updates with some fixes
* fix mask causality
* another commit that casts after
* add error
* simplify example
* update
* updates
* revert llama changes
* fix merge conflicts
* fix: tracing and metrics
* my updates
* update script default values
* fix block allocation issue
* fix prefill split attnetion mask
* no bugs
* add paged eager
* fix
* update
* style
* feat: add pytorch traces
* fix
* fix
* refactor: remove pytorch profiler data
* style
* nits
* cleanup
* draft test file
* fix
* fix
* fix paged and graphs
* small renamings
* cleanups and push
* refactor: move tracing and metrics logic to utils
* refactor: trace more blocks of code
* nits
* nits
* update
* to profile or not to profile
* refactor: create new output object
* causal by default
* cleanup but generations are still off for IDK what reason
* simplifications but not running still
* this does work.
* small quality of life updates
* nits
* updaet
* fix the scheduler
* fix warning
* ol
* fully fixed
* nits
* different generation parameters
* nice
* just style
* feat: add cache memory usage
* feat: add kv cache free memory
* feat: add active/waiting count & req latency
* do the sampling
* fix: synchronize CUDA only if available and improve error handling in ContinuousBatchingManager
* fix on mps
* feat: add dashboard & histogram buckets
* perf: improve waiting reqs data structures
* attempt to compile, but we should only do it on mps AFAIK
* feat: decouple scheduling logic
* just a draft
* c;eanup and fixup
* optional
* style
* update
* update
* remove the draft documentation
* fix import as well
* update
* fix the test
* style doomed
---------
Co-authored-by: Luc Georges <luc.sydney.georges@gmail.com>
* starting attn refactor for encoder decoder models via bart (eager + sdpa)
* flash attention works, remove unnecessary code
* flex attention support for bart!, gotta check if the renaming is not too aggressive
* some comments
* skip flex grad test for standalone as done with the other test
* revert flex attn rename (for now), sdpa simplify, and todos
* more todos
* refactor mask creation for reuse
* modular attempt at biogpt
* first batch of other models
* fix attn dropout
* fix autoformer copies
* hubert
* another batch of models
* copies/style + last round of bart models --> whisper next?
* remove unnecessary _reshape function and remove copy to whisper
* add skip for decoder-only models out of enc-dec (same as in bart)
* bring back licences
* remove comment, added to pr read instead
* mostly docs
* disable sew flex attn as it's unclear attn mask for now
* oops
* test fixes for enc-dec
* torch fx fixes + try at flex attn
* skip on mbart
* some more fixes
* musicgen skip / delete old attn class logic + sdpa compose compile skip
* disable flex attn for musicgen, not worth the effort
* more fixes and style
* flex attention test for dropout and encoder decoder that dont have main input names
* informer fixes
* the weirdest thing I've encountered yet...
* style
* remove empty tensor attempt, found core root in previous commits
* disable time series due to tests being very text centric on inputs
* add speech to text to be ignoring the other attns, also due to tests
* update docs
* remaining issues resolved ?
* update docs for current state --> nllb moe and pegasus x sdpa is questionable :D
* some models have not set the is_causal flag...
* change dtype in softmax tol old behaviour + some modular fixes
* I hate it but it is what it is
* fixes from main for bart
* forgot this one
* some model fixes
* style
* current status
* marian works now
* fixing some copies
* some copy fixes + time series x informer
* last models possibly and fixes on style/copies
* some post merge fixes
* more fixes
* make attention interface callable and move warnings there
* style lol
* add comment to "unsupported"
* remove callable interface and change interface warnings + some copies
* fix
* ternary is ugly af, make it simpler
* how did that happen
* fix flex attn test
* failing the test
* no more fallback! fixing copies next
* style + attn fixed
* fixing copies and mask creation
* wrong copy
* fixup tests and disable flex attn for now
* fixup last tests?
* _get_padding_size module
* do not patchify images when processing multi image
* modify llava onevision image processor fast
* tensor to list of tensors
* backward compat
* reuse pad_to_square in llave & some clarification
* add to doc
* fix: consider no image cases (text only or video)
* add integration test
* style & repo_consistency
* add seq_idx and fa kwargs
* update tests
* docs and grad ckpt support
* fmt
* better names
* test_raise_missing_padding_free_kwarg_errs
* + seq_idx in doc strings
* padding free training docs
* add link to pr plots
* raise err on attn_mask with padding free
* rm raising missing padding free err test
* BambaFlashAttentionKwargs
* run modular util for modular_granitemoehybrid.py
bnb quant tests: remove obsolete trust_remote_code test
The MPT model is now natively integrated in Transformers and no longer requires trust_remote_code=True. This removes the failing test_get_keys_to_not_convert_trust_remote_code and related usage, which depended on remote code and caused CI issues due to missing dependencies (e.g., triton_pre_mlir).
* fix sliding attn
* make style
* Update tests/test_modeling_common.py
Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
* no a second throught, should default to `True` fo BC
---------
Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
