.. |
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
há 9 meses atrás |
block_table.py
|
6ac658b0d6
some small performance improvements
|
há 5 meses atrás |
common.py
|
63b735bc2a
chore: optimize v2 block manager to match the performance of v1
|
há 6 meses atrás |
cpu_gpu_block_allocator.py
|
63b735bc2a
chore: optimize v2 block manager to match the performance of v1
|
há 6 meses atrás |
interfaces.py
|
63b735bc2a
chore: optimize v2 block manager to match the performance of v1
|
há 6 meses atrás |
naive_block.py
|
63b735bc2a
chore: optimize v2 block manager to match the performance of v1
|
há 6 meses atrás |
prefix_caching_block.py
|
6ac658b0d6
some small performance improvements
|
há 5 meses atrás |
utils.py
|
9099040472
feat: cross-attention kv caching support
|
há 6 meses atrás |