electron-rare/mlx-lm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
test_data
mlx-lm/tests
T
History
Awni Hannun abc52a0a48 Add deepseek v32 (#512) 
* deepseek v32

* Fix sparse token selection in deepseek v3.2 (#531)

* Fix sparse token selection in deepseek v3.2

* Fix 4D mask input handling and remove unnecessary ones array

* simplify

* Update mlx_lm/models/deepseek_v32.py

Co-authored-by: Tarjei Mandt <kernelpool@gmail.com>

* comments

---------

Co-authored-by: Tarjei Mandt <kernelpool@gmail.com>
2025-12-03 14:03:21 -08:00
..
test_chat.py
Add system prompt to chat script (#334)
2025-07-30 08:33:33 -07:00
test_datsets.py
dynamic dataset preprocessing (#54)
2025-03-27 08:32:51 -07:00
test_evaluate.py
Batch generation (#443)
2025-09-15 16:02:45 -07:00
test_finetune.py
DWQ for very large models (#536)
2025-11-07 06:43:40 -08:00
test_generate.py
Allow providing prompt caches in batched generation (#602)
2025-11-20 09:14:30 -08:00
test_gguf.py
version
2025-03-13 15:37:13 -07:00
test_losses.py
fix flaky test (#643)
2025-12-02 13:33:11 -08:00
test_models.py
Add deepseek v32 (#512)
2025-12-03 14:03:21 -08:00
test_prompt_cache.py
fix (#503)
2025-09-26 08:48:24 -07:00
test_sample_utils.py
Adding support for XTC (eXclude Top Choice) (#110)
2025-04-24 14:25:30 -07:00
test_server.py
Batching in the server (#626)
2025-12-03 13:14:18 -08:00
test_tokenizers.py
DWQ for very large models (#536)
2025-11-07 06:43:40 -08:00
test_tuner_trainer.py
DWQ for very large models (#536)
2025-11-07 06:43:40 -08:00
test_tuner_utils.py
version
2025-03-13 15:37:13 -07:00
test_utils.py
Cleanup and simplify model I/O (#532)
2025-10-07 06:57:51 -07:00