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
8b2b566ea710e48149886aecf2e17a2c78d55c11
vLLM
/
vllm
/
model_executor
/
layers
/
quantization
/
quark
T
History
xaguilar-amd
0b131b16c9
[ROCm][AITER][Quark] Tag per-channel FP8 weights as PER_CHANNEL so AITER pre-shuffled GEMM is selected (
#44626
)
...
Signed-off-by: Xavier Aguilar <
xavier.aguilarfruto@amd.com
>
2026-06-17 14:05:34 +00:00
..
schemes
[ROCm][AITER][Quark] Tag per-channel FP8 weights as PER_CHANNEL so AITER pre-shuffled GEMM is selected (
#44626
)
2026-06-17 14:05:34 +00:00
__init__.py
[Misc][Quark] Upstream Quark format to VLLM (
#10765
)
2025-01-15 11:05:15 -05:00
quark_moe.py
[MoE] Remove inplace fused experts mechanism (
#43727
)
2026-05-27 20:00:19 -07:00
quark.py
[Bugfix] Add deepseek_v32 to Quark dynamic MXFP4 model type check (
#39498
)
2026-06-10 02:52:33 -07:00
utils.py
[Quark] Support loading Quark NVFP4 checkpoints in vLLM (
#35859
)
2026-05-13 11:17:36 -07:00