Skip to content

Various cosmetic/comment fixes #12089

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 1 commit into from
Jan 16, 2025
Merged

Various cosmetic/comment fixes #12089

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def create_weights(self, layer: torch.nn.Module, input_size: int,

if not sparse_cutlass_supported():
raise ValueError(
"Sparse CUTLASS not supported. vLLM must be built with"
"Sparse CUTLASS not supported. vLLM must be built with "
"CUDA 12.2 or later to use this feature")

self.output_dtype = params_dtype
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/aria.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,8 +390,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/commandr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,8 +440,7 @@ def load_weights(self, weights: Iterable[Tuple[str,

if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/dbrx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -452,8 +452,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
for name, loaded_weight in weights:
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/exaone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -533,8 +533,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/gpt_j.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,8 +316,7 @@ def load_weights(self, weights: Iterable[Tuple[str,

if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/granite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -475,8 +475,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
7 changes: 3 additions & 4 deletions vllm/model_executor/models/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,9 +105,9 @@ def __init__(self,
max_position_embeddings: int = 8192,
quant_config: Optional[QuantizationConfig] = None,
bias: bool = False,
bias_o_proj: bool = False,
cache_config: Optional[CacheConfig] = None,
prefix: str = "",
bias_o_proj: bool = False) -> None:
prefix: str = "") -> None:
super().__init__()
layer_idx = extract_layer_index(prefix)
self.hidden_size = hidden_size
Expand Down Expand Up @@ -397,8 +397,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -431,8 +431,7 @@ def load_weights(self, weights: Iterable[Tuple[str,

if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/mllama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1432,8 +1432,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
loaded_weight = loaded_weight.view(loaded_weight.shape[0], -1)
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/nemotron.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -492,8 +492,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/phimoe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -626,8 +626,7 @@ def load_weights(self, weights: Iterable[Tuple[str,

if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/qwen2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,8 +367,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
3 changes: 1 addition & 2 deletions vllm/model_executor/models/solar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -492,8 +492,7 @@ def load_weights(self, weights: Iterable[Tuple[str,
continue
if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache scales for quark and
# compressed-tensors quantization
# Loading kv cache quantization scales
param = params_dict[scale_name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down
Loading