PR #844 fix gguf fp8 input model and vram issue

fix gguf fp8 input model issue

wenhuach21 committed 339 days ago

for debug, still has some oom issue

wenhuach21 committed 339 days ago

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 339 days ago

Merge branch 'main' into fix_gguf_fp8

wenhuach21 committed 339 days ago

refine a little

wenhuach21 committed 339 days ago

fix gguf

n1ck-guo committed 339 days ago

Merge branch 'main' into fix_gguf_fp8

n1ck-guo committed 338 days ago

clean

n1ck-guo committed 338 days ago

rm value error

wenhuach21 committed 338 days ago

auto-round fix gguf fp8 input model and vram issue #844 Merged