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
f6130145c827169cf152bf806f76d5b0fa4e6731
vLLM
/
vllm
/
model_executor
/
layers
/
quantization
/
quark
T
History
Wentao Ye
29c9af5211
[Kimi K3 Refactor] Add
UnfinalizedMoEOutput
proto following up for
#53152
(
#53310
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2026-08-24 11:21:11 -04:00
..
schemes
Support DeepSeek-V4 AMD Quark NVFP4 with emulation kernel (
#47972
)
2026-08-07 01:19:31 -07:00
__init__.py
[Misc][Quark] Upstream Quark format to VLLM (
#10765
)
2025-01-15 11:05:15 -05:00
quark_moe.py
[Kimi K3 Refactor] Add
UnfinalizedMoEOutput
proto following up for
#53152
(
#53310
)
2026-08-24 11:21:11 -04:00
quark.py
[Bugfix] Fix six quantization exception messages split across positional args (
#50479
)
2026-08-21 09:06:56 -07:00
utils.py
Fix Quark mxfp4 quantized model loading issue under mtp (
#46757
)
2026-07-16 14:58:47 -04:00