This website requires JavaScript.
Explore
Help
Register
Sign In
biondizzle
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
b28246f6ff1684ef166d04cc9185e113a8474696
vllm
/
vllm
/
v1
/
attention
/
backends
History
Sage Moore
b28246f6ff
[ROCm][V1][Bugfix] Add get_builder_cls method to the ROCmAttentionBackend class (
#14065
)
...
Signed-off-by: Sage Moore <
sage@neuralmagic.com
>
2025-03-01 07:18:32 +00:00
..
mla
[Attention] Flash MLA for V1 (
#13867
)
2025-02-27 23:03:41 +00:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
flash_attn.py
[Attention] MLA support for V1 (
#13789
)
2025-02-27 13:14:17 -05:00
pallas.py
[V1][TPU] Integrate the new ragged paged attention kernel with vLLM v1 on TPU (
#13379
)
2025-02-28 11:01:36 -07:00
rocm_attn.py
[ROCm][V1][Bugfix] Add get_builder_cls method to the ROCmAttentionBackend class (
#14065
)
2025-03-01 07:18:32 +00:00