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
78300cdabffbaaffe7625ed34412ec2aec75535c
vLLM
/
vllm
/
v1
/
worker
/
gpu
/
spec_decode
/
dflash
T
History
Giancarlo Delfin
facd9a74a1
[Model Runner V2][Spec Decode] Skip DP sync for all speculator uniform decodes (
#54856
)
2026-09-03 10:32:33 +00:00
..
__init__.py
[MRV2][Spec Decode] DFlash (
#44586
)
2026-06-10 08:47:46 -07:00
cudagraph.py
[Spec decode] Support Kimi-K3 DCP with DSpark (
#52188
)
2026-08-17 13:08:45 -07:00
speculator.py
[Model Runner V2][Spec Decode] Skip DP sync for all speculator uniform decodes (
#54856
)
2026-09-03 10:32:33 +00:00
utils.py
[Bugfix][Spec Decode] Take the DFlash draft's RoPE layout from its own config (
#54373
)
2026-08-31 18:13:20 -04:00