mirror of
https://github.com/huggingface/transformers.git
synced 2025-08-02 11:11:05 +06:00
633215ba58
* Draft version of new KV Caching This should allow Attention Sinks (https://github.com/tomaarsen/attention_sinks) / StreamingLLM (https://arxiv.org/abs/2309.17453) to be easily implemented in a third-party or in transformers directly * Address numerous PR suggestions 1. Move layer_idx from cache to ...Attention. Removes confusing set_layer_idx magic. 2. Always convert past_key_values to Cache instance at the start of ...Attention, removes all other isinstance calls. 3. Remove __bool__ and __getitem__ magic as they're confusing. 4. past_key_values.update(key, value, idx) now returns key, value. 5. Add use_legacy_cache flag, defaults to None, i.e. Falsey. This breaks generate for now, until 1) the cache is used is generate() or 2) use_legacy_cache is defaulted to True in generate() until we change it in another PR. 6. Separate key_cache and value_cache. Some work is still needed to see if the SinkCache can conveniently be implemented with just one update method. * Implement the SinkCache through backward+forward rotations * Integrate (Sink)Cache with Llama FA2 * Set use_legacy_cache=True as default, allows for test passes * Move from/to_legacy_cache to ...Model class * Undo unnecessary newline change * Remove copy utility from deprecated OpenLlama * Match import style * manual rebase with main * Cache class working with generate (#1) * Draft version of new KV Caching This should allow Attention Sinks (https://github.com/tomaarsen/attention_sinks) / StreamingLLM (https://arxiv.org/abs/2309.17453) to be easily implemented in a third-party or in transformers directly * Address numerous PR suggestions 1. Move layer_idx from cache to ...Attention. Removes confusing set_layer_idx magic. 2. Always convert past_key_values to Cache instance at the start of ...Attention, removes all other isinstance calls. 3. Remove __bool__ and __getitem__ magic as they're confusing. 4. past_key_values.update(key, value, idx) now returns key, value. 5. Add use_legacy_cache flag, defaults to None, i.e. Falsey. This breaks generate for now, until 1) the cache is used is generate() or 2) use_legacy_cache is defaulted to True in generate() until we change it in another PR. 6. Separate key_cache and value_cache. Some work is still needed to see if the SinkCache can conveniently be implemented with just one update method. * Integrate (Sink)Cache with Llama FA2 * Move from/to_legacy_cache to ...Model class * Undo unnecessary newline change * Match import style * working generate * Add tests; Simplify code; Apply changes to Mistral and Persimmon * fix rebase mess * a few more manual fixes * last manual fix * propagate changes to phi * upgrade test * add use_legacy_cache docstring; beef up tests * reintroduce unwanted deletes --------- Co-authored-by: Tom Aarsen <Cubiegamedev@gmail.com> * move import * add default to model_kwargs.get('use_legacy_cache') * correct failing test * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * apply PR suggestions * fix failing test * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Tom Aarsen <37621491+tomaarsen@users.noreply.github.com> * PR comments * tmp commit * add docstrings * more tests, more docstrings, add to docs * derp * tmp commit * tmp dbg * more dbg * fix beam search bug * cache can be a list of tuples in some models * fix group beam search * all but sinkcache integration tests * fix sink cache and add hard integration test * now also compatible with input_embeds input * PR comments * add Cache support to Phi+FA2 * make fixup --------- Co-authored-by: Joao Gante <joao@huggingface.co> Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> |
||
|---|---|---|
| .. | ||
| internal | ||
| main_classes | ||
| model_doc | ||
| tasks | ||
| _config.py | ||
| _redirects.yml | ||
| _toctree.yml | ||
| accelerate.md | ||
| add_new_model.md | ||
| add_new_pipeline.md | ||
| add_tensorflow_model.md | ||
| attention.md | ||
| autoclass_tutorial.md | ||
| benchmarks.md | ||
| bertology.md | ||
| big_models.md | ||
| chat_templating.md | ||
| community.md | ||
| contributing.md | ||
| create_a_model.md | ||
| custom_models.md | ||
| custom_tools.md | ||
| debugging.md | ||
| fast_tokenizers.md | ||
| generation_strategies.md | ||
| glossary.md | ||
| hpo_train.md | ||
| index.md | ||
| installation.md | ||
| llm_tutorial_optimization.md | ||
| llm_tutorial.md | ||
| model_memory_anatomy.md | ||
| model_sharing.md | ||
| model_summary.md | ||
| multilingual.md | ||
| notebooks.md | ||
| pad_truncation.md | ||
| peft.md | ||
| perf_hardware.md | ||
| perf_infer_cpu.md | ||
| perf_infer_gpu_one.md | ||
| perf_torch_compile.md | ||
| perf_train_cpu_many.md | ||
| perf_train_cpu.md | ||
| perf_train_gpu_many.md | ||
| perf_train_gpu_one.md | ||
| perf_train_special.md | ||
| perf_train_tpu_tf.md | ||
| perf_train_tpu.md | ||
| performance.md | ||
| perplexity.md | ||
| philosophy.md | ||
| pipeline_tutorial.md | ||
| pipeline_webserver.md | ||
| pr_checks.md | ||
| preprocessing.md | ||
| quantization.md | ||
| quicktour.md | ||
| run_scripts.md | ||
| sagemaker.md | ||
| serialization.md | ||
| task_summary.md | ||
| tasks_explained.md | ||
| testing.md | ||
| tf_xla.md | ||
| tflite.md | ||
| tokenizer_summary.md | ||
| torchscript.md | ||
| training.md | ||
| transformers_agents.md | ||
| troubleshooting.md | ||