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
c19c263ac8ea3fd6e1d2d689f0e4e725855d89cf
vLLM
/
vllm
/
model_executor
/
kernels
/
attention
/
dsa
T
History
Nicolò Lucchesi
30d4032363
[Model][GLM-5.3-Flash] Support DCP for the kpool sparse indexer (
#59211
)
...
Signed-off-by: NickLucche <
nicolo.lucchesi@mistral.ai
>
2026-10-05 16:44:14 +02:00
..
__init__.py
[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (
#46076
)
2026-07-01 00:32:20 -04:00
candidate_blocks.py
[Bugfix] Revert "[ROCm][Perf] Replace torch.topk in DSA candidate block selection" (
#59125
)
2026-09-28 20:11:48 -07:00
dcp_indexer_cutedsl.py
[Model][GLM-5.3-Flash] Support DCP for the kpool sparse indexer (
#59211
)
2026-10-05 16:44:14 +02:00
sparse_mqa_logits.py
[Bugfix][DSA] Bound DeepSelect sentinel columns in the sparse top-k remap (
#58215
)
2026-09-24 00:54:27 +00:00