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

[ Misc ] Enable Quantizing All Layers of DeekSeekv2 #6423

Merged
merged 2 commits into from
Jul 14, 2024
Merged

[ Misc ] Enable Quantizing All Layers of DeekSeekv2 #6423

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
459ac71
fixed deepseek fp8
robertgshaw2-neuralmagic Jul 14, 2024
da716b9
format
robertgshaw2-neuralmagic Jul 14, 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
2 changes: 1 addition & 1 deletion .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,6 @@ while getopts "m:b:l:f:t:" OPT; do
done

lm_eval --model vllm \
--model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,add_bos_token=true,distributed_executor_backend="ray",trust_remote_code=true \
--model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,add_bos_token=true,distributed_executor_backend="ray",trust_remote_code=true,max_model_len=4096 \
--tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
--batch_size $BATCH_SIZE
5 changes: 5 additions & 0 deletions vllm/model_executor/model_loader/weight_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -431,6 +431,11 @@ def convert_pyslice_to_tensor(x: Any) -> torch.Tensor:
def default_weight_loader(param: torch.Tensor,
loaded_weight: torch.Tensor) -> None:
"""Default weight loader."""
# If the weight on disk does not have a shape, give it one
# (such scales for AutoFp8).
if len(loaded_weight.shape) == 0:
loaded_weight = loaded_weight.reshape(1)

assert param.size() == loaded_weight.size()
param.data.copy_(loaded_weight)

Expand Down
Loading