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
2d7053438a112e2be55cf6d2bde9deb8a169d0a4
vLLM
/
vllm
/
model_executor
/
layers
/
quantization
/
quark
T
History
bnellnm
dc917cceb8
[MoE Refactor] Move
select_experts
from
FusedMoEQuantMethod
->
FusedMoE
(
#31996
)
...
Signed-off-by: Bill Nell <
bnell@redhat.com
>
2026-01-22 18:21:35 -05:00
..
schemes
[Bugfix] Suppress log on non-ROCm platform (
#32703
)
2026-01-20 13:38:20 -08:00
__init__.py
[Misc][Quark] Upstream Quark format to VLLM (
#10765
)
2025-01-15 11:05:15 -05:00
quark_moe.py
[MoE Refactor] Move
select_experts
from
FusedMoEQuantMethod
->
FusedMoE
(
#31996
)
2026-01-22 18:21:35 -05:00
quark.py
[Quantization] Support Quark int4-fp8 w4a8 for MoE (
#30071
)
2025-12-18 04:20:42 +00:00
utils.py
[ROCM] DSfp4 mla projection gemms weight dynamic quantization (
#32238
)
2026-01-15 14:13:08 -06:00