Skip to content

GitLab

Unverified Commit aaf0ad8c authored by Stefan He's avatar Stefan He Committed by GitHub
Browse files

remove vllm fp8quant from fp8.py (#8937)

parent 361379b5
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 3 deletions
python/sglang/srt/layers/quantization/fp8.py
View file @ aaf0ad8c
...@@ -98,9 +98,6 @@ if _is_hip and (_use_aiter or _use_hip_int4): ...@@ -98,9 +98,6 @@ if _is_hip and (_use_aiter or _use_hip_int4):
from aiter.fused_moe import fused_moe from aiter.fused_moe import fused_moe
from aiter.ops.shuffle import shuffle_weight from aiter.ops.shuffle import shuffle_weight
if not (_is_cuda or _is_npu or (_is_cpu and _is_cpu_amx_available) or _is_hip):
from vllm._custom_ops import scaled_fp8_quant
ACTIVATION_SCHEMES = ["static", "dynamic"] ACTIVATION_SCHEMES = ["static", "dynamic"]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment