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
main
vLLM
/
vllm
/
v1
/
worker
/
gpu
/
model_states
T
Add File
New File
Upload File
Apply Patch
Copy Permalink
Download directory as ZIP
Download directory as TAR.GZ
Delete Directory
History
Feanor
and
Taneem Ibrahim
5d5c3d7c43
[Bugfix] Preserve padding token types for cross encoders (
#58143
)
...
Signed-off-by: zhaoye <
772971548@qq.com
> Co-authored-by: Taneem Ibrahim <
taneem.ibrahim@gmail.com
>
2026-10-15 03:09:24 +00:00
..
__init__.py
[ModelRunnerV2] Support prompt embeds (
#42963
)
2026-08-17 21:58:50 +00:00
default.py
[Feat][Model] Support encoder-side SWA-bounded replay for DeepSeek-V4.1-Flash (
#56227
)
2026-09-18 15:01:24 -07:00
encoder_decoder.py
[MRV2] Miscellaneous code structure updates (
#60754
)
2026-10-09 17:58:09 -07:00
encoder_only.py
[Bugfix] Preserve padding token types for cross encoders (
#58143
)
2026-10-15 03:09:24 +00:00
interface.py
[Bugfix] Index Mamba align state copies by request slot in MRV2 (
#60210
)
2026-10-07 02:32:46 +00:00
mamba_hybrid.py
[Bugfix] Bound GDN speculative decode query widths (
#55504
)
2026-10-10 11:00:16 +08:00
mm_pruning.py
[Core][Model] Unify XD-RoPE into M-RoPE and derive the channel count (
#56078
)
2026-09-09 09:23:30 -07:00
prompt_embeds.py
[Bugfix][XPU] store the pointer raw bit pattern instead of its numeric value (
#54514
)
2026-09-24 02:05:26 -07:00
recoverssm.py
[Bugfix][RecoverSSM] Correct aligned state indices at exact block boundaries (
#59962
)
2026-10-12 02:08:14 +00:00