Skip to content

[Bugfix] Fix Mamba model initialization and MLP Speculator weights loading #10456

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 5 commits into from
Nov 20, 2024
Merged

[Bugfix] Fix Mamba model initialization and MLP Speculator weights loading #10456

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
dd6ee68
disable mamba weights tracker and fix mpl speculator
Isotr0py Nov 19, 2024
d642702
revert mamba weights tracking
Isotr0py Nov 19, 2024
d6ebd1f
revert mamba
Isotr0py Nov 20, 2024
30f4b2d
code format
Isotr0py Nov 20, 2024
852f077
code format
Isotr0py Nov 20, 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
8 changes: 2 additions & 6 deletions vllm/model_executor/models/mamba.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
"""PyTorch MAMBA model."""
from typing import Iterable, List, Optional, Set, Tuple
from typing import Iterable, List, Optional, Tuple

import torch
from torch import nn
Expand Down Expand Up @@ -243,10 +243,8 @@ def sample(
next_tokens = self.sampler(logits, sampling_metadata)
return next_tokens

def load_weights(self, weights: Iterable[Tuple[str,
torch.Tensor]]) -> Set[str]:
def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
params_dict = dict(self.named_parameters())
loaded_params: Set[str] = set()
for name, loaded_weight in weights:
if "A_log" in name:
name = name.replace("A_log", "A")
Expand All @@ -258,5 +256,3 @@ def load_weights(self, weights: Iterable[Tuple[str,
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
weight_loader(param, loaded_weight)
loaded_params.add(name)
return loaded_params
3 changes: 2 additions & 1 deletion vllm/model_executor/models/mlp_speculator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,8 @@ def load_weights(self, weights: Iterable[Tuple[str,
params_dict = dict(self.named_parameters())
loaded_params: Set[str] = set()
for name, loaded_weight in weights:
param = params_dict.get(name.replace("speculator.", ""))
name = name.replace("speculator.", "")
param = params_dict.get(name)
if param is not None:
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
Expand Down