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_v41
/
amd
T
History
frida-andersson
c077dc663d
[ROCm][Perf][DSv4.1] Enable decoder SWA bounded replay (
#59039
)
...
Signed-off-by: Frida Andersson <
fanderss@amd.com
>
2026-10-13 02:19:14 +00:00
..
mono
[ROCm][Perf][DSv4.1] Mono decode on every backbone layer (
#61082
)
2026-10-13 10:16:50 +08:00
__init__.py
[Refactor] Normalize DeepSeek V4.1 model package naming (
#56741
)
2026-09-13 23:17:50 -07:00
dspark.py
[Model][DSv4.1] Store the whole KV in MXFP8 (FlashMLA V4.1 record) (
#56893
)
2026-09-14 20:12:55 -07:00
model.py
[ROCm][Perf][DSv4.1] Enable decoder SWA bounded replay (
#59039
)
2026-10-13 02:19:14 +00:00
mono_decode.py
[ROCm][Perf][DSv4.1] Mono decode on every backbone layer (
#61082
)
2026-10-13 10:16:50 +08:00
rocm.py
[ROCm][Perf][DSv4.1] Mono decode layer for DeepSeek-V4.1-Flash on MI355X (
#60397
)
2026-10-09 20:53:18 -05:00
vl_model.py
[ROCm][Perf][DSv4.1] Enable decoder SWA bounded replay (
#59039
)
2026-10-13 02:19:14 +00:00