Skip to content

[None][chore] fix llmargs conflict #8152

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 3 commits into from
Oct 6, 2025
Merged

[None][chore] fix llmargs conflict #8152

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
70bfb91
init
Superjomn Oct 5, 2025
deed616
skip ray
Superjomn Oct 5, 2025
47e0635
skip rpc tests
Superjomn Oct 5, 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
9 changes: 1 addition & 8 deletions tensorrt_llm/llmapi/llm_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1550,7 +1550,7 @@ class BaseLlmArgs(StrictBaseModel):
description="Return perf metrics.",
status="prototype")

orchestrator_type: Optional[Literal["rpc"]] = Field(
orchestrator_type: Optional[Literal["rpc", "ray"]] = Field(
default=None,
description=
"The orchestrator type to use. Defaults to None, which uses MPI.",
Expand Down Expand Up @@ -2444,13 +2444,6 @@ class TorchLlmArgs(BaseLlmArgs):
status="prototype",
)

orchestrator_type: Optional[Literal["ray"]] = Field(
default=None,
description=
"The orchestrator type to use. Options: 'ray'. Defaults to None, which uses MPI.",
status="prototype",
)

# PrivateVars
_quant_config: Optional[QuantConfig] = PrivateAttr(default=None)

Expand Down
6 changes: 1 addition & 5 deletions tests/unittest/api_stability/references/llm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,10 +75,6 @@ methods:
annotation: Optional[str]
default: null
status: deprecated
orchestrator_type:
annotation: Optional[Literal['ray']]
default: null
status: prototype
build_config:
annotation: Optional[tensorrt_llm.llmapi.llm_args.BuildConfig]
default: null
Expand Down Expand Up @@ -184,7 +180,7 @@ methods:
default: False
status: prototype
orchestrator_type:
annotation: Optional[Literal["rpc"]]
annotation: Optional[Literal["rpc", "ray"]]
default: null
status: prototype
return_annotation: None
Expand Down
5 changes: 5 additions & 0 deletions tests/unittest/llmapi/test_llm_multi_gpu_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from .lora_test_utils import check_llama_7b_multi_lora_from_request_test_harness
from .test_llm_pytorch import llama_7b_lora_from_dir_test_harness
from .test_llm import _test_llm_capture_request_error
from utils.util import skip_ray
# isort: on
from tensorrt_llm.executor.rpc_proxy import GenerationExecutorRpcProxy
from tensorrt_llm.sampling_params import SamplingParams
Expand Down Expand Up @@ -61,6 +62,8 @@ def test_llama_7b_multi_lora_tp2():
cuda_graph_config=None)


@pytest.mark.skip(reason="https://nvbugs/5560921")
@skip_ray
@pytest.mark.gpu2
def test_llm_rpc_tp2():
with LLM(model=llama_model_path,
Expand All @@ -78,6 +81,8 @@ def test_llm_rpc_tp2():
assert len(res.outputs[0].token_ids) == 10


@pytest.mark.skip(reason="https://nvbugs/5560921")
@skip_ray
@pytest.mark.gpu2
@pytest.mark.asyncio
async def test_llm_rpc_streaming_tp2():
Expand Down
4 changes: 4 additions & 0 deletions tests/unittest/llmapi/test_llm_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -956,6 +956,8 @@ def test_max_num_token_check(self):
llm.generate([ids])


@pytest.mark.skip(reason="https://nvbugs/5560921")
@skip_ray
def test_llm_rpc():
# TODO: remove the with-statement when shutdown hang issue is fixed
with LLM(model=llama_model_path,
Expand All @@ -972,6 +974,8 @@ def test_llm_rpc():
assert len(res.outputs[0].token_ids) == 10


@pytest.mark.skip(reason="https://nvbugs/5560921")
@skip_ray
@pytest.mark.asyncio
async def test_llm_rpc_streaming():
# TODO: remove the with-statement when shutdown hang issue is fixed
Expand Down