zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-07-17 07:51:12 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
0989c073b0
mlx-examples/llms/mlx_lm
History
Gökdeniz Gülmez 0989c073b0
Optimizations for mamba1 (#1213) 
* added mx.einsum() operations: before: 41.293 tokens-per-sec, after: 57.822 tokens-per-sec

* Fused Operations in delta, B, C = ... :. Before: 57.822 tokens-per-sec, after: 83.890 tokens-per-sec

* Pre-computing A_log. After: 83.890 tokens-per-sec, before: 85.848 tokens-per-sec

* Update MambaBlock, Batched Input Processing, Improved Cache Handling, Pre-computed Constants, Cleaner State Management, Explicit Return Values:. Before: 82.442 tokens-per-sec, after: 129.130 tokens-per-sec.

* cleaning up and adding apple copyright to helium modelfile

* update Copyright to this year

* nits + even faster

---------

Co-authored-by: Awni Hannun <awni.hannun@gmail.com>
2025-02-03 13:36:08 -08:00
..
examples only download local shard (#1240) 2025-02-02 13:58:44 -08:00
models Optimizations for mamba1 (#1213) 2025-02-03 13:36:08 -08:00
tuner Fix no validation in lora (#1241) 2025-02-03 09:55:24 -08:00
__init__.py Fix detokenizer space match for quote (#1072) 2024-10-27 15:06:07 -07:00
_version.py deepseek v3 model with pipeline parallelism (#1191) 2025-01-09 15:55:53 -08:00
cache_prompt.py fix encoding with special tokens + chat template (#1189) 2025-01-03 10:50:59 -08:00
chat.py fix encoding with special tokens + chat template (#1189) 2025-01-03 10:50:59 -08:00
convert.py override dtype with quant (#1062) 2024-10-22 09:56:45 -07:00
evaluate.py Add support for fewshot and apply chat template lm_eval functionality (#1180) 2025-01-06 07:58:43 -08:00
fuse.py Adding full finetuning (#903) 2024-09-29 17:12:47 -07:00
generate.py Add a speculative decoding generator (#1155) 2025-01-10 15:27:08 -08:00
gguf.py Fix export to gguf (#993) 2024-09-20 13:33:45 -07:00
LORA.md Custom local dataset features (#1085) 2025-01-13 10:01:18 -08:00
lora.py fix(lora): add back store_true default args (#1205) 2025-01-16 11:15:42 -08:00
MANAGE.md Add model management functionality for local caches (#736) 2024-05-03 12:20:13 -07:00
manage.py Improvements to mlx_lm.manage (#1178) 2025-01-01 07:25:57 -08:00
MERGE.md Create executables for generate, lora, server, merge, convert (#682) 2024-04-16 16:08:49 -07:00
merge.py Create executables for generate, lora, server, merge, convert (#682) 2024-04-16 16:08:49 -07:00
py.typed Add py.typed to support PEP-561 (type-hinting) (#389) 2024-01-30 21:17:38 -08:00
README.md feat: move lora into mlx-lm (#337) 2024-01-23 08:44:37 -08:00
requirements.txt deepseek v3 model with pipeline parallelism (#1191) 2025-01-09 15:55:53 -08:00
sample_utils.py batched min p and fix spec gen sampling (#1222) 2025-01-27 15:40:31 -08:00
SERVER.md Fix object property value in mlx_lm.server chat completions response to match OpenAI spec (#1119) 2024-11-24 16:37:37 -08:00
server.py chore(mlx-lm): support text type content in messages (#1225) 2025-01-27 17:13:50 -08:00
tokenizer_utils.py Change the eos-token argument for mlx_lm.generate (#1176) 2025-01-05 22:26:05 -08:00
UPLOAD.md Mlx llm package (#301) 2024-01-12 10:25:56 -08:00
utils.py only download local shard (#1240) 2025-02-02 13:58:44 -08:00

README.md

Generate Text with MLX and 🤗 Hugging Face

This an example of large language model text generation that can pull models from the Hugging Face Hub.

For more information on this example, see the README in the parent directory.

This package also supports fine tuning with LoRA or QLoRA. For more information see the LoRA documentation.