biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
73f48ce559e230fd0d738c52cb2e99bd0dd08754
vllm/tests/quantization/test_fp8.py
Jonas M. Kübler 98e7f223b9 enable skipping of SW attention layers when using FP8 KV cache (#33695) 
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
2026-03-27 07:25:02 -06:00

18 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink