This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
fce10dbed5441b4f918b23a2b63aae72bc00a2f6
vLLM
/
vllm
/
v1
/
core
T
History
Russell Bryant
98aa16ff41
[v1] Add cross-attention KV cache support for encoder-decoder models (
#23664
)
...
Signed-off-by: Russell Bryant <
rbryant@redhat.com
>
2025-08-26 18:49:06 +00:00
..
sched
[v1] Add cross-attention KV cache support for encoder-decoder models (
#23664
)
2025-08-26 18:49:06 +00:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
block_pool.py
[BugFix] Fix stuck stats/metrics after requests are aborted (
#22995
)
2025-08-20 13:50:29 +08:00
encoder_cache_manager.py
[Bugfix] Fix scheduling when repeated images in one request (
#23544
)
2025-08-26 09:46:28 +00:00
kv_cache_coordinator.py
[v1] Add cross-attention KV cache support for encoder-decoder models (
#23664
)
2025-08-26 18:49:06 +00:00
kv_cache_manager.py
[v1] Add cross-attention KV cache support for encoder-decoder models (
#23664
)
2025-08-26 18:49:06 +00:00
kv_cache_utils.py
[v1] Move block_hashes from KVCacheManager to Request.block_hashes (
#19728
)
2025-08-15 16:52:52 -07:00
single_type_kv_cache_manager.py
[v1] Add cross-attention KV cache support for encoder-decoder models (
#23664
)
2025-08-26 18:49:06 +00:00