Skip to content

fix (NvBug 5354925): Fix static EPLB #5411

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
Jun 25, 2025
Merged

fix (NvBug 5354925): Fix static EPLB #5411

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
08d49ae
fix
syuoni Jun 24, 2025
0050719
unwaive
syuoni Jun 24, 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
3 changes: 3 additions & 0 deletions examples/ep_load_balancer/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ Run 32-way expert parallelism inference on the prepared dataset. Please refer to
cat > ./extra_llm_api_options.yaml <<EOF
enable_attention_dp: true
use_cuda_graph: true
moe_backend: WideEP
moe_max_num_tokens: 8192
EOF

Expand Down Expand Up @@ -116,6 +117,7 @@ Run 36-way expert parallelism inference with the EPLB configuration incorporated
cat > ./extra_llm_api_options_eplb.yaml <<EOF
enable_attention_dp: true
use_cuda_graph: true
moe_backend: WideEP
moe_max_num_tokens: 9216
moe_load_balancer: ./moe_load_balancer.yaml
EOF
Expand Down Expand Up @@ -181,6 +183,7 @@ Run 36-way expert parallelism inference with the EPLB configuration incorporated
cat > ./extra_llm_api_options_eplb.yaml <<EOF
enable_attention_dp: true
use_cuda_graph: true
moe_backend: WideEP
moe_max_num_tokens: 9216
moe_load_balancer: ./moe_load_balancer.yaml
EOF
Expand Down
8 changes: 4 additions & 4 deletions tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,7 +196,7 @@ def __init__(
hidden_size, self.num_slots)
else:
raise NotImplementedError(
f"Not available alltoall method type: {alltoall_method_type!r}"
f"Not available alltoall method type: {self.alltoall_method_type!r}"
)

# If True, the router weight will be multiplied on the input rather than at the end of FC2
Expand Down Expand Up @@ -433,7 +433,7 @@ def forward_chunk(
token_selected_slots, dtype=token_final_scales.dtype)
else:
raise NotImplementedError(
f"Not available alltoall method type: {alltoall_method_type!r}"
f"Not available alltoall method type: {self.alltoall_method_type!r}"
)

x_sf = None
Expand Down Expand Up @@ -552,7 +552,7 @@ def forward_chunk(
)
else:
raise NotImplementedError(
f"Not available alltoall method type: {alltoall_method_type!r}"
f"Not available alltoall method type: {self.alltoall_method_type!r}"
)

if self.enable_alltoall:
Expand Down Expand Up @@ -631,7 +631,7 @@ def forward_chunk(
deep_ep_topk_weights, deep_ep_handle)
else:
raise NotImplementedError(
f"Not available alltoall method type: {alltoall_method_type!r}"
f"Not available alltoall method type: {self.alltoall_method_type!r}"
)

if self.layer_load_balancer and not self.layer_load_balancer.is_static_routing(
Expand Down
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,4 +441,3 @@ accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp=vanilla-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5354946)
examples/test_multimodal.py::test_llm_multimodal_general[kosmos-2-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5354936)
examples/test_multimodal.py::test_llm_multimodal_general[fuyu-8b-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5354936)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_4gpus_static_eplb SKIP (https://nvbugs/5354925)