This website requires JavaScript.
Explore
Help
Sign In
xinyun
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced
2025-12-09 23:54:56 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
vllm
/
tests
/
v1
/
attention
History
TJian
1ee5ead5f8
[ROCm] [V1] [SpecDec] Enable Speculative Decoding on ROCm V1 Engine (
#21496
)
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-08-07 19:13:17 -07:00
..
test_attention_backends.py
Add tree attention backend for v1 (part 1) (
#20401
)
2025-08-03 22:13:26 -07:00
test_attention_splitting.py
[Attention][DBO] Add support for "splitting" the CommonAttentionMetadata (
#21153
)
2025-08-01 19:47:53 -07:00
test_chunked_local_attention.py
[Misc] Add unit tests for chunked local attention (
#21692
)
2025-07-31 11:39:16 -07:00
test_mamba_selectors.py
[v1][mamba] Added mamba_type into MambaSpec (
#21715
)
2025-07-28 08:15:55 +00:00
utils.py
[ROCm] [V1] [SpecDec] Enable Speculative Decoding on ROCm V1 Engine (
#21496
)
2025-08-07 19:13:17 -07:00