Skip to content

Fix arg checking for GGUF/Quark/GPTQMarlin quantized MoE methods #17491

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix arg checking for GGUF/Quark/GPTQMarlin quantized MoE methods #17491

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
f76ceae
Fix arg checking for a few quantized MoE methods
mgoin Apr 30, 2025
fd5077b
Merge branch 'main' into assert-no-ep-gguf
mgoin May 2, 2025
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
1 change: 1 addition & 0 deletions vllm/model_executor/layers/quantization/gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -343,6 +343,7 @@ def apply(
activation: str = "silu",
):
assert activation == "silu", "Only SiLU activation is supported."
assert expert_map is None, "Expert maps not supported yet"
if apply_router_weight_on_input:
raise NotImplementedError(
"Apply router weight on input is not supported for"
Expand Down
2 changes: 1 addition & 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 @@ -607,7 +607,7 @@ def apply(
activation: str = "silu",
) -> torch.Tensor:
assert activation == "silu", "Only SiLU activation is supported."
if apply_router_weight_on_input is not None:
if apply_router_weight_on_input:
raise NotImplementedError(
"Apply router weight on input is not supported for"
"fused Marlin MoE method.")
Expand Down
1 change: 1 addition & 0 deletions vllm/model_executor/layers/quantization/quark/quark_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,7 @@ def apply(
topk_weights=topk_weights,
topk_ids=topk_ids,
inplace=True,
activation=activation,
use_fp8_w8a8=True,
global_num_experts=global_num_experts,
apply_router_weight_on_input=apply_router_weight_on_input,
Expand Down