Skip to content

Fix DeepSeekV2 AWQ#56

Open
gau-nernst wants to merge 5 commits intomingfeima:cpu_opt_ww11from
gau-nernst:fix_awq
Open

Fix DeepSeekV2 AWQ#56
gau-nernst wants to merge 5 commits intomingfeima:cpu_opt_ww11from
gau-nernst:fix_awq

Conversation

@gau-nernst
Copy link

A quick fix for #43 due to FP8 changes.

For testing (same as before)

python -m sglang.launch_server --model TechxGenus/DeepSeek-V2-Lite-Chat-AWQ --device cpu --disable-overlap-schedule --dtype bfloat16 --trust-remote-code

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant