mirror of
https://github.com/exo-explore/exo.git
synced 2026-01-29 08:12:04 -05:00
Compare commits
2 Commits
aiohttp
...
disable-md
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c3b7bba580 | ||
|
|
9e58a57599 |
14
README.md
14
README.md
@@ -107,6 +107,10 @@ uv run exo
|
||||
|
||||
This starts the exo dashboard and API at http://localhost:52415/
|
||||
|
||||
|
||||
*Please view the section on RDMA to enable this feature on MacOS >=26.2!*
|
||||
|
||||
|
||||
### Run from Source (Linux)
|
||||
|
||||
**Prerequisites:**
|
||||
@@ -230,7 +234,7 @@ This removes:
|
||||
|
||||
RDMA is a new capability added to macOS 26.2. It works on any Mac with Thunderbolt 5 (M4 Pro Mac Mini, M4 Max Mac Studio, M4 Max MacBook Pro, M3 Ultra Mac Studio).
|
||||
|
||||
Note that on Mac Studio, you cannot use the Thunderbolt 5 port next to the Ethernet port.
|
||||
Please refer to the caveats for immediate troubleshooting.
|
||||
|
||||
To enable RDMA on macOS, follow these steps:
|
||||
|
||||
@@ -247,6 +251,14 @@ To enable RDMA on macOS, follow these steps:
|
||||
|
||||
After that, RDMA will be enabled in macOS and exo will take care of the rest.
|
||||
|
||||
**Important Caveats**
|
||||
|
||||
1. Devices that wish to be part of an RDMA cluster must be connected to all other devices in the cluster.
|
||||
2. The cables must support TB5.
|
||||
3. On a Mac Studio, you cannot use the Thunderbolt 5 port next to the Ethernet port.
|
||||
4. If running from source, please use the script found at `tmp/set_rdma_network_config.sh`, which will disable Thunderbolt Bridge and set dhcp on each RDMA port.
|
||||
5. RDMA ports may be unable to discover each other on different versions of MacOS. Please ensure that OS versions match exactly (even beta version numbers) on all devices.
|
||||
|
||||
---
|
||||
|
||||
### Using the API
|
||||
|
||||
@@ -90,7 +90,6 @@ class Node:
|
||||
worker = Worker(
|
||||
node_id,
|
||||
session_id,
|
||||
connection_message_receiver=router.receiver(topics.CONNECTION_MESSAGES),
|
||||
global_event_receiver=router.receiver(topics.GLOBAL_EVENTS),
|
||||
local_event_sender=router.sender(topics.LOCAL_EVENTS),
|
||||
command_sender=router.sender(topics.COMMANDS),
|
||||
@@ -227,9 +226,6 @@ class Node:
|
||||
self.worker = Worker(
|
||||
self.node_id,
|
||||
result.session_id,
|
||||
connection_message_receiver=self.router.receiver(
|
||||
topics.CONNECTION_MESSAGES
|
||||
),
|
||||
global_event_receiver=self.router.receiver(
|
||||
topics.GLOBAL_EVENTS
|
||||
),
|
||||
|
||||
@@ -7,7 +7,6 @@ from anyio import CancelScope, create_task_group, fail_after
|
||||
from anyio.abc import TaskGroup
|
||||
from loguru import logger
|
||||
|
||||
from exo.routing.connection_message import ConnectionMessage, ConnectionMessageType
|
||||
from exo.shared.apply import apply
|
||||
from exo.shared.models.model_cards import ModelId
|
||||
from exo.shared.types.api import ImageEditsInternalParams
|
||||
@@ -57,7 +56,6 @@ class Worker:
|
||||
node_id: NodeId,
|
||||
session_id: SessionId,
|
||||
*,
|
||||
connection_message_receiver: Receiver[ConnectionMessage],
|
||||
global_event_receiver: Receiver[ForwarderEvent],
|
||||
local_event_sender: Sender[ForwarderEvent],
|
||||
# This is for requesting updates. It doesn't need to be a general command sender right now,
|
||||
@@ -74,7 +72,6 @@ class Worker:
|
||||
self.event_index_counter = event_index_counter
|
||||
self.command_sender = command_sender
|
||||
self.download_command_sender = download_command_sender
|
||||
self.connection_message_receiver = connection_message_receiver
|
||||
self.event_buffer = OrderedBuffer[Event]()
|
||||
self.out_for_delivery: dict[EventId, ForwarderEvent] = {}
|
||||
|
||||
@@ -105,7 +102,6 @@ class Worker:
|
||||
tg.start_soon(info_gatherer.run)
|
||||
tg.start_soon(self._forward_info, info_recv)
|
||||
tg.start_soon(self.plan_step)
|
||||
tg.start_soon(self._connection_message_event_writer)
|
||||
tg.start_soon(self._resend_out_for_delivery)
|
||||
tg.start_soon(self._event_applier)
|
||||
tg.start_soon(self._forward_events)
|
||||
@@ -279,41 +275,6 @@ class Worker:
|
||||
instance = self.state.instances[task.instance_id]
|
||||
return instance.shard_assignments.node_to_runner[self.node_id]
|
||||
|
||||
async def _connection_message_event_writer(self):
|
||||
with self.connection_message_receiver as connection_messages:
|
||||
async for msg in connection_messages:
|
||||
await self.event_sender.send(
|
||||
self._convert_connection_message_to_event(msg)
|
||||
)
|
||||
|
||||
def _convert_connection_message_to_event(self, msg: ConnectionMessage):
|
||||
match msg.connection_type:
|
||||
case ConnectionMessageType.Connected:
|
||||
return TopologyEdgeCreated(
|
||||
conn=Connection(
|
||||
source=self.node_id,
|
||||
sink=msg.node_id,
|
||||
edge=SocketConnection(
|
||||
sink_multiaddr=Multiaddr(
|
||||
address=f"/ip4/{msg.remote_ipv4}/tcp/{msg.remote_tcp_port}"
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
case ConnectionMessageType.Disconnected:
|
||||
return TopologyEdgeDeleted(
|
||||
conn=Connection(
|
||||
source=self.node_id,
|
||||
sink=msg.node_id,
|
||||
edge=SocketConnection(
|
||||
sink_multiaddr=Multiaddr(
|
||||
address=f"/ip4/{msg.remote_ipv4}/tcp/{msg.remote_tcp_port}"
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
async def _nack_request(self, since_idx: int) -> None:
|
||||
# We request all events after (and including) the missing index.
|
||||
# This function is started whenever we receive an event that is out of sequence.
|
||||
|
||||
49
tmp/set_rdma_network_config.sh
Executable file
49
tmp/set_rdma_network_config.sh
Executable file
@@ -0,0 +1,49 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
PREFS="/Library/Preferences/SystemConfiguration/preferences.plist"
|
||||
|
||||
# Remove bridge0 interface
|
||||
ifconfig bridge0 &>/dev/null && {
|
||||
ifconfig bridge0 | grep -q 'member' && {
|
||||
ifconfig bridge0 | awk '/member/ {print $2}' | xargs -n1 ifconfig bridge0 deletem 2>/dev/null || true
|
||||
}
|
||||
ifconfig bridge0 destroy 2>/dev/null || true
|
||||
}
|
||||
|
||||
# Remove Thunderbolt Bridge from VirtualNetworkInterfaces in preferences.plist
|
||||
/usr/libexec/PlistBuddy -c "Delete :VirtualNetworkInterfaces:Bridge:bridge0" "$PREFS" 2>/dev/null || true
|
||||
|
||||
networksetup -listlocations | grep -q exo || {
|
||||
networksetup -createlocation exo
|
||||
}
|
||||
|
||||
networksetup -switchtolocation exo
|
||||
networksetup -listallhardwareports \
|
||||
| awk -F': ' '/Hardware Port: / {print $2}' \
|
||||
| while IFS=":" read -r name; do
|
||||
case "$name" in
|
||||
"Ethernet Adapter"*)
|
||||
;;
|
||||
"Thunderbolt Bridge")
|
||||
;;
|
||||
"Thunderbolt "*)
|
||||
networksetup -listallnetworkservices \
|
||||
| grep -q "EXO $name" \
|
||||
|| networksetup -createnetworkservice "EXO $name" "$name" 2>/dev/null \
|
||||
|| continue
|
||||
networksetup -setdhcp "EXO $name"
|
||||
;;
|
||||
*)
|
||||
networksetup -listallnetworkservices \
|
||||
| grep -q "$name" \
|
||||
|| networksetup -createnetworkservice "$name" "$name" 2>/dev/null \
|
||||
|| continue
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
networksetup -listnetworkservices | grep -q "Thunderbolt Bridge" && {
|
||||
networksetup -setnetworkserviceenabled "Thunderbolt Bridge" off
|
||||
} || true
|
||||
Reference in New Issue
Block a user