mirror of
https://github.com/exo-explore/exo.git
synced 2026-02-04 19:22:39 -05:00
Compare commits
2 Commits
rust-explo
...
leo/acknow
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4909d87c58 | ||
|
|
7b6cad94c6 |
4
.github/workflows/pipeline.yml
vendored
4
.github/workflows/pipeline.yml
vendored
@@ -142,4 +142,6 @@ jobs:
|
||||
# Run pytest outside sandbox (needs GPU access for MLX)
|
||||
export HOME="$RUNNER_TEMP"
|
||||
export EXO_TESTS=1
|
||||
EXO_RESOURCES_DIR="$PWD/resources" $TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib
|
||||
export EXO_DASHBOARD_DIR="$PWD/dashboard/"
|
||||
export EXO_RESOURCES_DIR="$PWD/resources"
|
||||
$TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib
|
||||
|
||||
@@ -69,7 +69,8 @@
|
||||
# Create wrapper scripts
|
||||
for script in exo exo-master exo-worker; do
|
||||
makeWrapper ${exoVenv}/bin/$script $out/bin/$script \
|
||||
--set DASHBOARD_DIR ${self'.packages.dashboard} \
|
||||
--set EXO_DASHBOARD_DIR ${self'.packages.dashboard} \
|
||||
--set EXO_RESOURCES_DIR ${inputs.self + "/resources"} \
|
||||
${lib.optionalString pkgs.stdenv.isDarwin "--prefix PATH : ${pkgs.macmon}/bin"}
|
||||
done
|
||||
'';
|
||||
|
||||
@@ -39,7 +39,7 @@ RESOURCES_DIR = (
|
||||
)
|
||||
_DASHBOARD_DIR_ENV = os.environ.get("EXO_DASHBOARD_DIR", None)
|
||||
DASHBOARD_DIR = (
|
||||
find_dashboard() if _RESOURCES_DIR_ENV is None else Path.home() / _RESOURCES_DIR_ENV
|
||||
find_dashboard() if _DASHBOARD_DIR_ENV is None else Path.home() / _DASHBOARD_DIR_ENV
|
||||
)
|
||||
|
||||
# Log files (data/logs or cache)
|
||||
|
||||
@@ -125,7 +125,6 @@ def main(
|
||||
event_sender.send(
|
||||
TaskStatusUpdated(task_id=task.task_id, task_status=TaskStatus.Running)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
match task:
|
||||
case ConnectToGroup() if isinstance(
|
||||
current_status, (RunnerIdle, RunnerFailed)
|
||||
@@ -137,6 +136,7 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
group = initialize_mlx(bound_instance)
|
||||
|
||||
logger.info("runner connected")
|
||||
@@ -153,6 +153,7 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
def on_model_load_timeout() -> None:
|
||||
event_sender.send(
|
||||
@@ -195,6 +196,7 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
logger.info(f"warming up inference for instance: {instance}")
|
||||
if ModelTask.TextGeneration in shard_metadata.model_card.tasks:
|
||||
@@ -234,6 +236,8 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
assert model and not isinstance(model, DistributedImageModel)
|
||||
assert tokenizer
|
||||
|
||||
@@ -365,6 +369,7 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
try:
|
||||
# Generate images using the image generation backend
|
||||
@@ -430,6 +435,7 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
try:
|
||||
image_index = 0
|
||||
@@ -488,6 +494,8 @@ def main(
|
||||
runner_id=runner_id, runner_status=current_status
|
||||
)
|
||||
)
|
||||
event_sender.send(TaskAcknowledged(task_id=task.task_id))
|
||||
|
||||
current_status = RunnerShutdown()
|
||||
case _:
|
||||
raise ValueError(
|
||||
|
||||
@@ -201,29 +201,29 @@ def test_events_processed_in_correct_order(patch_out_mlx: pytest.MonkeyPatch):
|
||||
TaskStatusUpdated(
|
||||
task_id=INITIALIZATION_TASK_ID, task_status=TaskStatus.Running
|
||||
),
|
||||
TaskAcknowledged(task_id=INITIALIZATION_TASK_ID),
|
||||
RunnerStatusUpdated(
|
||||
runner_id=RUNNER_1_ID, runner_status=RunnerConnecting()
|
||||
),
|
||||
TaskAcknowledged(task_id=INITIALIZATION_TASK_ID),
|
||||
TaskStatusUpdated(
|
||||
task_id=INITIALIZATION_TASK_ID, task_status=TaskStatus.Complete
|
||||
),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerConnected()),
|
||||
TaskStatusUpdated(task_id=LOAD_TASK_ID, task_status=TaskStatus.Running),
|
||||
TaskAcknowledged(task_id=LOAD_TASK_ID),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerLoading()),
|
||||
TaskAcknowledged(task_id=LOAD_TASK_ID),
|
||||
TaskStatusUpdated(task_id=LOAD_TASK_ID, task_status=TaskStatus.Complete),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerLoaded()),
|
||||
TaskStatusUpdated(task_id=WARMUP_TASK_ID, task_status=TaskStatus.Running),
|
||||
TaskAcknowledged(task_id=WARMUP_TASK_ID),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerWarmingUp()),
|
||||
TaskAcknowledged(task_id=WARMUP_TASK_ID),
|
||||
TaskStatusUpdated(task_id=WARMUP_TASK_ID, task_status=TaskStatus.Complete),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerReady()),
|
||||
TaskStatusUpdated(
|
||||
task_id=CHAT_COMPLETION_TASK_ID, task_status=TaskStatus.Running
|
||||
),
|
||||
TaskAcknowledged(task_id=CHAT_COMPLETION_TASK_ID),
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerRunning()),
|
||||
TaskAcknowledged(task_id=CHAT_COMPLETION_TASK_ID),
|
||||
expected_chunk,
|
||||
TaskStatusUpdated(
|
||||
task_id=CHAT_COMPLETION_TASK_ID, task_status=TaskStatus.Complete
|
||||
@@ -231,10 +231,10 @@ def test_events_processed_in_correct_order(patch_out_mlx: pytest.MonkeyPatch):
|
||||
# CHAT COMPLETION TASK SHOULD COMPLETE BEFORE RUNNER READY
|
||||
RunnerStatusUpdated(runner_id=RUNNER_1_ID, runner_status=RunnerReady()),
|
||||
TaskStatusUpdated(task_id=SHUTDOWN_TASK_ID, task_status=TaskStatus.Running),
|
||||
TaskAcknowledged(task_id=SHUTDOWN_TASK_ID),
|
||||
RunnerStatusUpdated(
|
||||
runner_id=RUNNER_1_ID, runner_status=RunnerShuttingDown()
|
||||
),
|
||||
TaskAcknowledged(task_id=SHUTDOWN_TASK_ID),
|
||||
TaskStatusUpdated(
|
||||
task_id=SHUTDOWN_TASK_ID, task_status=TaskStatus.Complete
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user