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
94de871546e8da687c08ed8a7e0a26531500d4bd
vLLM
/
vllm
/
model_executor
/
layers
/
quantization
/
quark
/
schemes
T
History
Charlie Fu
fe5438200b
[Rocm][Bugfix] Fix dtype not same for gemm_a4w4 op (
#33734
)
...
Signed-off-by: charlifu <
charlifu@amd.com
>
2026-02-06 19:09:59 +00:00
..
__init__.py
[Feature][OCP MX] Support mxfp6 and mixed mxfp6-mxfp4 (
#21166
)
2025-10-07 09:35:26 -04:00
quark_ocp_mx.py
[Rocm][Bugfix] Fix dtype not same for gemm_a4w4 op (
#33734
)
2026-02-06 19:09:59 +00:00
quark_scheme.py
Update
Optional[x]
->
x | None
and
Union[x, y]
to
x | y
(
#26633
)
2025-10-12 09:51:31 -07:00
quark_w8a8_fp8.py
[Refactor] Make FP8 Linear Ops use kernel abstraction (
#27814
)
2026-01-20 14:48:20 +08:00
quark_w8a8_int8.py
[Refactor] Make FP8 Linear Ops use kernel abstraction (
#27814
)
2026-01-20 14:48:20 +08:00