Instructions to use GenomaLabs-com/kv-cache-eviction-mla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GenomaLabs-com/kv-cache-eviction-mla with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GenomaLabs-com/kv-cache-eviction-mla", dtype="auto") - Notebooks
- Google Colab
- Kaggle
GENOMA LABS / research commited on
Commit ·
d6db53d
1
Parent(s): 1ba26d6
cleanup: gitignore pycache + remove stray empty CSV from earlier debug run
Browse files
.gitignore
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
__pycache__/
|
| 2 |
+
*.pyc
|
| 3 |
+
*.pyo
|
| 4 |
+
.ipynb_checkpoints/
|
| 5 |
+
.DS_Store
|
results/validate_random_init.csv
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
step,max_cache_size,avg_cache_size,expected_cap,over_cap
|
|
|
|
|
|
src/__pycache__/kv_eviction_mla.cpython-311.pyc
DELETED
|
Binary file (14 kB)
|
|
|