This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
382970ee6ca490aeaaaf4e32c53695b581ff61ba
vLLM
/
vllm
/
model_executor
/
kernels
/
attention
/
dsa
T
History
Woosuk Kwon
38537331d3
[Bugfix][DSA] Avoid runtime JIT for offset candidate end buffers (
#57667
)
...
Signed-off-by: Woosuk Kwon <
woosuk@inferact.ai
>
2026-09-19 00:27:11 -07:00
..
__init__.py
[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (
#46076
)
2026-07-01 00:32:20 -04:00
candidate_blocks.py
[Bugfix][DSv4.1] Preserve NaN-scored candidate block indices (
#57454
)
2026-09-17 19:00:10 -07:00
dcp_indexer_cutedsl.py
[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (
#53566
)
2026-09-12 00:05:59 -04:00
sparse_mqa_logits.py
[Bugfix][DSA] Avoid runtime JIT for offset candidate end buffers (
#57667
)
2026-09-19 00:27:11 -07:00