books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Qwen3 KV cache (#688)

Browse Source
This commit is contained in:
Sebastian Raschka
2025-06-21 17:34:39 -05:00
committed by GitHub
parent 2a530b49fe
commit 0b15a00574
8 changed files with 370 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pkg/llms_from_scratch/tests/test_llama3.py
View File

@@ -189,7 +189,7 @@ def llama3_weights_path(tmp_path_factory):
)
@pytest.mark.parametrize("ModelClass", [Llama3Model, Llama3ModelKV])
@pytest.mark.parametrize("generate_fn", [generate_text_simple, generate_text_simple_cached])
def test_gpt_model_variants(ModelClass, generate_fn, llama3_weights_path):
def test_model_variants(ModelClass, generate_fn, llama3_weights_path):
# Skip incompatible combinations
if generate_fn is generate_text_simple and getattr(ModelClass, "reset_kv_cache", False):