optimum
aba7f46d - add_exllamav2 (#1419)

Commit

1 year ago

add_exllamav2 (#1419) * add_exllamav2 * style * fix doc * fix doc * raise error * Update docs/source/llm_quantization/usage_guides/quantization.mdx Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com> * update doc * update min version of autogptq --------- Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>

References

#1419 - add_exllamav2

Author

SunMarc

Parents

f6adbef5

Files4

docs/source/llm_quantization/usage_guides
- quantization.mdx
optimum
- gptq
  - quantizer.py
- utils
  - import_utils.py
tests/gptq
- test_quantization.py

optimum aba7f46d - add_exllamav2 (#1419)

optimum
aba7f46d - add_exllamav2 (#1419)