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
/
models
/
deepseek_v4
/
amd
T
History
AMD-yanfeiwang
and
aoshen02
e3bbaf2369
[ROCm][DSv4] Fuse the shared expert into AITER MegaMoE (
#61004
)
...
Signed-off-by: Yanfei Wang <
yanfei.wang@amd.com
> Co-authored-by: aoshen02 <
aoshen@inferact.ai
>
2026-10-12 15:53:16 +08:00
..
__init__.py
[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (
#43004
)
2026-05-18 19:50:02 -07:00
dspark.py
[ROCm][DSv4] AITER MegaMoEV2 Integration For DeepSeek V4 (
#59685
)
2026-10-07 09:35:53 -05:00
mega_moe.py
[ROCm][DSv4] Fuse the shared expert into AITER MegaMoE (
#61004
)
2026-10-12 15:53:16 +08:00
model.py
[ROCm][DSv4] Fuse the shared expert into AITER MegaMoE (
#61004
)
2026-10-12 15:53:16 +08:00
mtp.py
[ROCm][DSv4] AITER MegaMoEV2 Integration For DeepSeek V4 (
#59685
)
2026-10-07 09:35:53 -05:00
rocm.py
[ROCm][DSv4][Perf] Use the shared prefill chunk plan in the ROCm sparse prefill (
#58405
)
2026-09-30 15:26:57 +08:00