[Quantization] AutoGPTQ refactor and matmul combination support #694
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Please cc @MasterJH5574 |
MasterJH5574
force-pushed
the
lei/gptq-combined
branch
from
9976004
to
1efef2a
Compare
MasterJH5574
changed the title
MasterJH5574
force-pushed
the
lei/gptq-combined
branch
2 times, most recently
from
8e0400a
to
b5c1162
Compare
|
LGTM, thanks for your hard work on this pr @MasterJH5574 ! |
MasterJH5574
approved these changes
Aug 16, 2023
This PR refactors the AutoGPTQ integration to better align with the framework design. The PR, meanwhile, supports the AutoGPTQ quantization in MLC LLM with matmul combination. With this PR, you will be able to compile Llama2 using the following command: ```python python -m mlc_llm.build --model=Llama-2-7b-chat-hf --quantization autogptq_llama_q4f16_1 --target cuda ``` to use the AutoGPTQ quantization. **Note that the first run may take around 10 min for AutoGPTQ quantization computation, and the following runs will be much quicker.** The AutoGPTQ quantization requires the Python `auto_gptq` package to have version at least 0.2.0. Co-authored-by: Lei Wang <LeiWang1999@users.noreply.github.com>
MasterJH5574
force-pushed
the
lei/gptq-combined
branch
from
b5c1162
to
823d481
Compare
|
do you also think this should be added in the requirements? auto_gptq module not working in macos unfortunately |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR refactors the AutoGPTQ integration to better align with the framework design. The PR, meanwhile, supports the AutoGPTQ quantization in MLC LLM with matmul combination.
With this PR, you will be able to compile Llama2 using the following command:
to use the AutoGPTQ quantization. Note that the first run may take around 10 min for AutoGPTQ quantization computation, and the following runs will be much quicker. The AutoGPTQ quantization requires the Python
auto_gptqpackage to have version at least 0.2.0.Co-authored-by: Ruihang Lai ruihangl@cs.cmu.edu