 Sebastian Raschka
|
80d4732456
add HF equivalency tests for standalone nbs (#774)
|
há 3 meses atrás |
|
Sebastian Raschka
|
c6472f1af1
Update Python dependency in pyproject.toml (#748)
|
há 4 meses atrás |
|
Sebastian Raschka
|
a354555049
Batched KV Cache Inference for Qwen3 (#735)
|
há 4 meses atrás |
|
Sebastian Raschka
|
9cf64170ed
Update Qwen3 tokenizer test (#727)
|
há 4 meses atrás |
|
Sebastian Raschka
|
0405b0c8e7
Handle other Qwen3 tokenizer settings (#716)
|
há 4 meses atrás |
|
Sebastian Raschka
|
c4ec55edac
Support different Qwen3 sizes in pkg (#714)
|
há 4 meses atrás |
|
Sebastian Raschka
|
37b26c2e04
CPU compile performance for Qwen3 models (#704)
|
há 5 meses atrás |
|
Sebastian Raschka
|
0a2e8c39c4
Qwen3 KV cache (#688)
|
há 5 meses atrás |
|
Sebastian Raschka
|
3be0f3202a
Llama 3 KV Cache (#685)
|
há 5 meses atrás |
|
Sebastian Raschka
|
e719bd86ad
Qwen3 From Scratch (#678)
|
há 5 meses atrás |
|
Sebastian Raschka
|
c4cde1c21b
Reduce Llama 3 RoPE memory requirements (#658)
|
há 5 meses atrás |
|
Sebastian Raschka
|
43e25a5165
Llama3Fast (#593)
|
há 7 meses atrás |
|
Sebastian Raschka
|
aedad7efc3
Add Llama 3.2 to pkg (#591)
|
há 7 meses atrás |
|
Sebastian Raschka
|
3f93d73d6d
Alt weight loading code via PyTorch (#585)
|
há 7 meses atrás |
|
Sebastian Raschka
|
ffd4035144
Add GPTModelFast (#584)
|
há 7 meses atrás |
|
Sebastian Raschka
|
c21bfe4a23
Add PyPI package (#576)
|
há 8 meses atrás |
|
Sebastian Raschka
|
bca82a9443
Simplify the setup in CI (#542)
|
há 9 meses atrás |
 ridhachahed
|
03d72e6eb5
Fixing small typo in package description of the pyproject.toml file (#533)
|
há 9 meses atrás |
|
Sebastian Raschka
|
a08d7aaa84
Uv workflow improvements (#531)
|
há 9 meses atrás |
|
Sebastian Raschka
|
3e3dc3c5dc
Native uv docs (#530)
|
há 9 meses atrás |