GPTQ support on ROCm #1489
Merged
GPTQ support on ROCm #1489
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
fxmarty
commented
Jan 25, 2024
| @@ -75,8 +75,8 @@ RUN chmod +x ~/mambaforge.sh && \ | |||
| mamba init && \ | |||
| rm ~/mambaforge.sh | |||
|
|
|||
| # Install PyTorch nightly (2.2.0.dev2023) compiled against RoCm 5.7, as VLLM can not be compiled with RoCm 5.6. | |||
| RUN pip install --pre torch==2.2.0.dev20231106 --index-url https://download.pytorch.org/whl/nightly/rocm5.7 | |||
There was a problem hiding this comment.
This nightly version was removed from https://download.pytorch.org/whl/nightly/rocm5.7
fxmarty
commented
Jan 25, 2024
Comment on lines
170
to
173
| if torch.equal(g_idx, torch.tensor([i // groupsize for i in range(self.infeatures)], dtype=torch.int32, device=g_idx.device)): | ||
| self.g_idx = None | ||
| else: | ||
| self.g_idx = g_idx |
There was a problem hiding this comment.
Fixes a bug in the original exllamav2 code.
fxmarty
commented
Jan 25, 2024
Comment on lines
192
to
188
| # We NEED to keep a pointer on Python side, otherwise the garbage collector will mess with us, | ||
| # and `Memory access fault by GPU node-2` will EAT you. | ||
| self.temp_dq = temp_dq |
There was a problem hiding this comment.
This gave me headaches today.
There was a problem hiding this comment.
THIS is what was crashing TP>1?
There was a problem hiding this comment.
@Narsil can we test this quickly? If that's the case that would be amazing.
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
OlivierDehaene
force-pushed
the
gptq-rocm
branch
from
088f8e7
to
7d2bc40
Compare
helena-intel
pushed a commit
to helena-intel/text-generation-inference-hf
that referenced
this pull request
Feb 1, 2024
Tested with ``` CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq EXLLAMA_VERSION=1 CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq CUDA_VISIBLE_DEVICES="0,1" text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq ``` all with good and identical results on MI210. --------- Co-authored-by: Felix Marty <felix@hf.co> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
kdamaszk
pushed a commit
to kdamaszk/tgi-gaudi
that referenced
this pull request
Apr 29, 2024
Tested with ``` CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq EXLLAMA_VERSION=1 CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq CUDA_VISIBLE_DEVICES="0,1" text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq ``` all with good and identical results on MI210. --------- Co-authored-by: Felix Marty <felix@hf.co> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
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.
Tested with
all with good and identical results on MI210.