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
f7ef489e93cf92b8d6ce7403b49f1db867bcc35e
vLLM
/
vllm
/
models
/
deepseek_v32
T
History
Woosuk Kwon
e644c8cd8c
[Perf] Optimize DeepSeek V3.2 sequence parallelism (
#51434
)
...
Signed-off-by: Woosuk Kwon <
woosuk@inferact.ai
>
2026-08-07 16:51:01 -07:00
..
amd
[Perf] Narrow DeepSeek V3.2 eager CUDA graph region (
#51425
)
2026-08-07 14:37:43 -07:00
common
[Perf][CUDA] Programmatic dependent launch for the DSA decode kernels (
#50230
)
2026-08-06 00:53:17 -07:00
nvidia
[Perf] Optimize DeepSeek V3.2 sequence parallelism (
#51434
)
2026-08-07 16:51:01 -07:00
__init__.py
[ROCm]Migrating Deepseek V3.2 to vllm/models/deepseek_v32/ (
#47207
)
2026-07-30 08:37:43 -05:00
attention.py
[Perf] Narrow DeepSeek V3.2 eager CUDA graph region (
#51425
)
2026-08-07 14:37:43 -07:00