Arcweld - Revision history

Ampdot at 01:19, 29 August 2025

2025-08-29T01:19:30Z

← Older revision		Revision as of 01:19, 29 August 2025
Line 19:		Line 19:

	* [[Elysium]]		* [[Elysium]]
			[[Category:Infrastructure]]

Ampdot: /* Setup instructions */

2025-07-10T04:54:08Z

Setup instructions

← Older revision		Revision as of 04:54, 10 July 2025
Line 14:		Line 14:
	#* Some VPNs are incompatible and you may need to disable them.		#* Some VPNs are incompatible and you may need to disable them.
	# Join using a Tailscale invite link		# Join using a Tailscale invite link
	# If you've been granted login access, `ssh sparks@arcweld` to access the shared inference account. '''You may have to reboot for it to work.'''		# If you've been granted login access, `ssh sparks@arcweld` to access the shared inference account. '''You may have to reboot for it to work.''' You can also try manually editing the machine IPv4 inside Tailscale portal to something random that doesn't conflict with your LAN.

	== See also ==		== See also ==

	* [[Elysium]]		* [[Elysium]]

Ampdot at 00:33, 28 June 2025

2025-06-28T00:33:13Z

← Older revision		Revision as of 00:33, 28 June 2025
Line 1:		Line 1:
	'''Arcweld''' is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it memory bandwidth per dollar ~~as a~~ training ~~rig~~), although it isn't forbidden.		'''Arcweld''' is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it isn't the ideal way to purchase memory bandwidth per dollar (critical for training), although it isn't forbidden.

	== Specifications ==		== Specifications ==

Ampdot at 00:28, 28 June 2025

2025-06-28T00:28:44Z

← Older revision		Revision as of 00:28, 28 June 2025
Line 1:		Line 1:
	'''Arcweld''' is a ~~proposed~~ server ~~intended~~ for the primary goal of experimenting with novel LLM inference technologies~~, the secondary goals of a~~) reducing the cost of using hosted APIs when it would not interfere with the primary goal and ~~b) providing space~~ to ~~train models~~.		'''Arcweld''' is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it memory bandwidth per dollar as a training rig), although it isn't forbidden.

			== Specifications ==

			* Mac Studio M3 Ultra
			** 819 GB/s memory bandwidth
			** 60-core GPU
			** 32-core Neural Engine
			* 512GB Unified Memory

			== Setup instructions ==

			# Download and install [https://tailscale.com/ Tailscale]
			#* Some VPNs are incompatible and you may need to disable them.
			# Join using a Tailscale invite link
			# If you've been granted login access, `ssh sparks@arcweld` to access the shared inference account. '''You may have to reboot for it to work.'''

			== See also ==

			* [[Elysium]]

Ampdot: Created page with "'''Arcweld''' is a proposed server intended for the primary goal of experimenting with novel LLM inference technologies, the secondary goals of a) reducing the cost of using hosted APIs when it would not interfere with the primary goal and b) providing space to train models."

2024-09-23T07:55:57Z

Created page with "'''Arcweld''' is a proposed server intended for the primary goal of experimenting with novel LLM inference technologies, the secondary goals of a) reducing the cost of using hosted APIs when it would not interfere with the primary goal and b) providing space to train models."

New page

'''Arcweld''' is a proposed server intended for the primary goal of experimenting with novel LLM inference technologies, the secondary goals of a) reducing the cost of using hosted APIs when it would not interfere with the primary goal and b) providing space to train models.