Alex Barron 85ffd2c96a Quantized KV Cache (#1075) ...

* add QuantizedKVCache

* simplify

* add tests

* single sdpa function

* fix sed

* in place

* fix tests

* support different k and v head dims

2024-10-31 16:59:52 -07:00

..

test_datsets.py

Configuration-based use of HF hub-hosted datasets for training (#701)

2024-06-26 10:20:50 -07:00

test_finetune.py

Feature: QDoRA (#891)

2024-09-30 08:01:11 -07:00

test_generate.py

repetiton_penalty and logits_bias just using logits_processors (#1004)

2024-09-30 08:49:03 -07:00

test_gguf.py

fix(mlx-lm): type hints in gguf.py (#621)

2024-03-26 07:56:01 -07:00

test_models.py

More cache improvements (#1015)

2024-10-07 20:45:51 -07:00

test_prompt_cache.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

test_sample_utils.py

Faster sampling with mx.compile (#937)

2024-08-15 11:29:09 -07:00

test_server.py

Prompt caching in mlx_lm.server (#1026)

2024-10-14 10:57:22 -07:00

test_tokenizers.py

Fix detokenizer space match for quote (#1072)

2024-10-27 15:06:07 -07:00

test_tuner_utils.py

LoRA: Extract small function (#614)

2024-06-02 06:38:42 -07:00

test_utils_load_model.py

support load model by custom get_model_classes (#899)

2024-07-25 11:01:17 -07:00

test_utils.py

Fix whipser conversion for safetensors models (#935)

2024-08-14 10:22:04 -07:00