Skip to content

[Bugfix] Fix awq_marlin and gptq_marlin flags #6745

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

Merged
merged 2 commits into from
Jul 25, 2024
Merged

[Bugfix] Fix awq_marlin and gptq_marlin flags #6745

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
430d5ea
fix awq_marlin and gptq_marlin flags
alexm-redhat Jul 24, 2024
4cb2a17
ping
alexm-redhat Jul 24, 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
5 changes: 3 additions & 2 deletions vllm/model_executor/layers/quantization/awq_marlin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ class AWQMarlinConfig(QuantizationConfig):
def __init__(self, weight_bits: int, group_size: int, has_zp: bool,
lm_head_quantized: bool) -> None:
self.weight_bits = weight_bits
self.pack_factor = 32 // self.weight_bits # packed into int32
self.pack_factor = 32 // self.weight_bits # packed into 32bits
self.group_size = group_size
self.has_zp = has_zp
self.lm_head_quantized = lm_head_quantized
Expand Down Expand Up @@ -69,7 +69,8 @@ def from_config(cls, config: Dict[str, Any]) -> "AWQMarlinConfig":
def override_quantization_method(cls, hf_quant_cfg,
user_quant) -> Optional[str]:
can_convert = cls.is_awq_marlin_compatible(hf_quant_cfg)
is_valid_user_quant = (user_quant is None or user_quant == "marlin")
is_valid_user_quant = (user_quant is None or user_quant == "marlin"
or user_quant == "awq_marlin")

if can_convert and is_valid_user_quant:
msg = ("The model is convertible to {} during runtime."
Expand Down
3 changes: 2 additions & 1 deletion vllm/model_executor/layers/quantization/gptq_marlin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,8 @@ def override_quantization_method(cls, hf_quant_cfg,
user_quant) -> Optional[str]:
can_convert = cls.is_gptq_marlin_compatible(hf_quant_cfg)

is_valid_user_quant = (user_quant is None or user_quant == "marlin")
is_valid_user_quant = (user_quant is None or user_quant == "marlin"
or user_quant == "gptq_marlin")

if can_convert and is_valid_user_quant:
msg = ("The model is convertible to {} during runtime."
Expand Down