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

Jump to bottom

Enable Dynamic MoE for Mixtral on 1.19.0 #425

Merged
merged 7 commits into from
Oct 25, 2024
Merged

Enable Dynamic MoE for Mixtral on 1.19.0 #425

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d4c2559
Add Dynamic MoE for bfloat16
tpawlows Oct 23, 2024
1a77e8b
vllm-hpu-extension SHA update
tpawlows Oct 24, 2024
0580f4a
Merge branch 'habana_main' into dev/tpawlowski/dynamic_moe_to_1_19
tpawlows Oct 25, 2024
1defd52
sort imports correctly in layer.py
tpawlows Oct 25, 2024
a9a4dbd
correctly sorted and formatted imports
tpawlows Oct 25, 2024
526ff02
fix code formatting for yapf
tpawlows Oct 25, 2024
30234cc
Merge branch 'habana_main' into dev/tpawlowski/dynamic_moe_to_1_19
tpawlows Oct 25, 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 requirements-hpu.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,4 +8,4 @@ pandas
tabulate
setuptools>=61
setuptools-scm>=8
vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@341a77f
vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@341a77f
22 changes: 15 additions & 7 deletions vllm/model_executor/layers/fused_moe/layer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,9 +226,13 @@ def __init__(
self.num_expert_group = num_expert_group
self.topk_group = topk_group
self.custom_routing_function = custom_routing_function
if current_platform.is_hpu():
from vllm_hpu_extension.ops import StaticFusedMOE
self.hpu_static_fused_moe = StaticFusedMOE(self.num_experts)
if is_hpu:
from vllm_hpu_extension.ops import DynamicFusedMOE, StaticFusedMOE

from vllm.model_executor.layers.quantization.inc import INCConfig
selected_fused_moe = (StaticFusedMOE if isinstance(
quant_config, INCConfig) else DynamicFusedMOE)
self.hpu_static_fused_moe = selected_fused_moe(self.num_experts)

if quant_config is None:
self.quant_method: Optional[QuantizeMethodBase] = (
Expand Down Expand Up @@ -321,8 +325,10 @@ def _load_w13(self,
expert_data.copy_(loaded_weight)

if is_hpu:
self.hpu_static_fused_moe.w13_list[expert_id].set_weight(
orig_exp_data)
from vllm_hpu_extension.ops import StaticFusedMOE
if isinstance(self.hpu_static_fused_moe, StaticFusedMOE):
self.hpu_static_fused_moe.w13_list[expert_id].set_weight(
orig_exp_data)

def _load_w2(self,
expert_data: torch.Tensor,
Expand All @@ -341,8 +347,10 @@ def _load_w2(self,
# w2, down_proj: Load into only logical weight of w2.
expert_data.copy_(loaded_weight)
if is_hpu:
self.hpu_static_fused_moe.w2_list[expert_id].set_weight(
expert_data)
from vllm_hpu_extension.ops import StaticFusedMOE
if isinstance(self.hpu_static_fused_moe, StaticFusedMOE):
self.hpu_static_fused_moe.w2_list[expert_id].set_weight(
expert_data)

def _load_single_value(self, param: torch.nn.Parameter,
loaded_weight: torch.Tensor, expert_id: int):
Expand Down
Loading