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
4e5ca89cfe98121642d76b40e32a006f4d0fbf3b
vLLM
/
vllm
/
models
T
History
Fangzhou Ai
and
Claude
4e5ca89cfe
[ROCm][MiniMax-M3] Cross-layer lightning-indexer top-k sharing (
#47269
)
...
Signed-off-by: Fangzhou Ai <
fangzhouai@gmail.com
> Co-authored-by: Claude <
noreply@anthropic.com
>
2026-07-01 10:50:09 +00:00
..
deepseek_v4
[ROCm][Perf][Bugfix] DSv4 indexer: use platform FP8 dtype (fnuz) for Q-quant on gfx942 (
#46730
)
2026-07-01 17:33:55 +08:00
deepseek_v32
[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (
#46076
)
2026-07-01 00:32:20 -04:00
minimax_m3
[ROCm][MiniMax-M3] Cross-layer lightning-indexer top-k sharing (
#47269
)
2026-07-01 10:50:09 +00:00
__init__.py
[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (
#43004
)
2026-05-18 19:50:02 -07:00