fastest way to move llms between machines for distributed inference
@digitalix2.8万 位关注者
74,754 次观看
33 条评论
评论来自 X (Twitter) 上的原帖

@mohandsdl
Maybe it’s a stupid question but do you need to have the models on all four machines in order to distribute the computing?
6 个赞

@digitalix
yes
6 个赞

@WihlSilentH
I remember moving a megabyte or two file onto a floppy 💾 disk and waiting. Or burning a few hundred megabytes on a CD 💿 ROM. Now we’re doing hundreds of Gigabytes in a minute lol
5 个赞

@dreamsofcode_io
HAYAI!
4 个赞

@tomosman
bruh at least mark this NSFW
4 个赞

@AffinityTechWx
TB5: 374 GB / 50 s ≈ 7.5 GB/s (~60 Gbps) over Finder's SMB 3.x. rsync/rclone or NFSv4 + jumbo frames add ~30%, pushing closer to ~80 Gbps. 10GbE: NVMe write-back cache on LVM RAID-5 NAS → TB-scale, NVMe-speed, low-cost model loads at a fraction of PCIe 5.0 NVMe cost #MLOps
3 个赞

@HenkPoley
Or I guess, plug that Thunderbolt 5 cable into the other Mac directly.
2 个赞

@Be3bZilla
Awesome👌🏾
2 个赞

@TheZachMueller
Good man. Now slap 2 on there and use RAID 😈
2 个赞

@MgkMshrmBrkfst
'move' glm4.7? just delete it
2 个赞

@usetraceix
Have you never heard of rsync?
2 个赞

@intspg
Insane how far we’ve come is there a moored law for file transfer speed 😂
2 个赞

@yeabu369
cool, can you send the the 3 other hardware to my addy when you're done hah
1 个赞

@unimatrixZxero
This is my sign to finally invest in TB5 enclosures
1 个赞

@KenrikMarch
Very nice 👍
1 个赞

@kiranadimatyam
This is freaking awesome.
1 个赞

@Doge_Codes
@Stocktrader nice tip
1 个赞

@SirNullptr
heads up buddy
1 个赞

@realGuySimple
You gonna use exo?

@EntropicIrony
Does this model interface well with openclaw? Wondering if the local models really can replace the api calls










