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
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
..
schemes
[Rocm][Bugfix] Fix dtype not same for gemm_a4w4 op (
#33734
)
2026-02-06 19:09:59 +00:00
__init__.py
[Misc][Quark] Upstream Quark format to VLLM (
#10765
)
2025-01-15 11:05:15 -05:00
quark_moe.py
[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (
#33375
)
2026-02-05 18:07:18 +00:00
quark.py
[Misc] Replace Optional[X] with X | None syntax (
#33332
)
2026-01-30 01:56:59 -08:00
utils.py
[ROCM] DSfp4 mla projection gemms weight dynamic quantization (
#32238
)
2026-01-15 14:13:08 -06:00