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
b0e9cff5e7f7dc4180ff0cd9380f9dcc2933c2f7
vLLM
/
vllm
/
models
T
History
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
d5f5de7a7d
[Bugfix] Fix DeepSeek V4 mHC broadcast buffer for weight sync (
#52626
)
...
Signed-off-by: Hollow Man <
hollowman@opensuse.org
>
2026-08-18 10:55:37 +08:00
..
common
[DSV4] Implement Sequence Parallelism (
#46789
)
2026-08-01 10:22:33 -07:00
deepseek_v4
[Bugfix] Fix DeepSeek V4 mHC broadcast buffer for weight sync (
#52626
)
2026-08-18 10:55:37 +08:00
deepseek_v32
[Spec Decode][Perf] Fuse the MTP trailing all-reduce; local-argmax draft tokens (
#49793
)
2026-08-14 17:07:07 -07:00
dots3_note
[Bugfix] Disable sequence parallelism for Dots3 NOTE (
#52172
)
2026-08-13 22:13:00 +08:00
inkling
[Bugfix] Support HF-config compat for Inkling (
#51850
)
2026-08-11 15:32:28 -04:00
kimi_k3
[Spec decode] Support Kimi-K3 DCP with DSpark (
#52188
)
2026-08-17 13:08:45 -07:00
minimax_m3
[Config] Unify indexer cache dtype under attention_config.indexer_kv_dtype (
#52550
)
2026-08-17 10:20:04 +08:00
__init__.py
[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (
#43004
)
2026-05-18 19:50:02 -07:00