Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added SRAM_SLICER_SHARED_MME_INPUT_EXPANSION_ENABLED envar to the readme, in AutoGPTQ #305

Merged
merged 3 commits into from
Jul 18, 2024
Merged

Added SRAM_SLICER_SHARED_MME_INPUT_EXPANSION_ENABLED envar to the readme, in AutoGPTQ #305

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
478333c
Added SRAM_SLICER_SHARED_MME_INPUT_EXPANSION_ENABLED envar to the rea…
HolyFalafel Jul 17, 2024
d681e1f
Update README.md with temp solution remark
HolyFalafel Jul 17, 2024
758a496
Update README.md
HolyFalafel Jul 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions examples/text-generation/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -512,11 +512,18 @@ For more details see [documentation](https://docs.habana.ai/en/latest/PyTorch/Mo
Llama2-7b in UINT4 weight only quantization is enabled using [AutoGPTQ Fork](https://github.com/HabanaAI/AutoGPTQ), which provides quantization capabilities in PyTorch.
Currently, the support is for UINT4 inference of pre-quantized models only.

You can run a *UINT4 weight quantized* model using AutoGPTQ with the argument `--gptq`.
You can run a *UINT4 weight quantized* model using AutoGPTQ by setting the following environment variables:
`SRAM_SLICER_SHARED_MME_INPUT_EXPANSION_ENABLED=false ENABLE_EXPERIMENTAL_FLAGS=true` before running the command,
and by adding the argument `--gptq`.

***Note:***
Setting the above environment variables improves performance. These variables will be removed in future releases.


Here is an example to run a quantized model on Llama2-7b `TheBloke/Llama-2-7b-Chat-GPTQ`:
```bash
python run_generation.py \
SRAM_SLICER_SHARED_MME_INPUT_EXPANSION_ENABLED=false \
ENABLE_EXPERIMENTAL_FLAGS=true python run_generation.py \
--attn_softmax_bf16 \
--model_name_or_path TheBloke/Llama-2-7b-Chat-GPTQ \
--use_hpu_graphs \
Expand Down