[HN Gopher] Amazon launches Trainium3
       ___________________________________________________________________
        
       Amazon launches Trainium3
        
       Author : thnaks
       Score  : 101 points
       Date   : 2025-12-02 19:04 UTC (3 hours ago)
        
 (HTM) web link (techcrunch.com)
 (TXT) w3m dump (techcrunch.com)
        
       | aaa_aaa wrote:
       | Interesting that in the article, they do not say what the chip
       | actually does. Not even once.
        
         | egorfine wrote:
         | Probably because the only task this chip has to perform is to
         | please shareholders hence there is no need to explain anything
         | to us peasant developers.
        
           | caminante wrote:
           | Time to go squat on trainium4.com [0]
           | 
           | [0] https://www.godaddy.com/domainsearch/find?domainToCheck=t
           | rai...
        
         | wmf wrote:
         | Training. It's in the name.
        
           | cobolcomesback wrote:
           | Ironically these chips are being targeted at inference as
           | well (the AWS CEO acknowledged the difficulties in naming
           | things during the announcement).
        
             | wmf wrote:
             | The same thing happened to AMD and Gaudi. They couldn't get
             | training to work so they pivoted to inference.
        
         | Kye wrote:
         | Vector math
        
         | Symmetry wrote:
         | A bunch of 128x128 systolic arrays at its heart. More details:
         | 
         | https://newsletter.semianalysis.com/p/amazons-ai-self-suffic...
        
       | nimbius wrote:
       | the real news is: "and teases an Nvidia-friendly roadmap"
       | 
       | The sole reason amazon is throwing any money at this is because
       | they think they can do to AI what they did with logistics and
       | shipping in an effort to slash costs leading into a recession (we
       | cant fire anyone else.) The hubris is magnanimous to say the
       | least.
       | 
       | but the total confidence is very low...so "Nvidia friendly" is
       | face saving to ensure no bridges they currently cross for AWS
       | profit get burned.
        
       | ZeroCool2u wrote:
       | I've had to repeatedly tell our AWS account reps that we're not
       | even a little interested in the Trainium or Inferentia instances
       | unless they have a provably reliable track record of working with
       | the standard libraries we have to use like Transformers and
       | PyTorch.
       | 
       | I know they claim they work, but that's only on their happy path
       | with their very specific AMI's and the nightmare that is the
       | neuron SDK. You try to do any real work with them and use your
       | own dependencies and things tend to fall apart immediately.
       | 
       | It was just in the past couple years that it really became
       | worthwhile to use TPU's if you're on GCP and that's only with the
       | huge investment on Google's part into software support. I'm not
       | going to sink hours and hours into beta testing AWS's software
       | just to use their chips.
        
         | ecshafer wrote:
         | IMO AWS once you get off the core services is full of beta
         | services. S3, Dynamo, Lambda, ECS, etc are all solid. But there
         | are a lot of services they have that have some big rough
         | patches.
        
           | kentm wrote:
           | I'd add SQS to the solid category.
           | 
           | But yes, the less of a core building block the specific
           | service is (or widely used internally in Amazon), the more
           | likely you are to run into significant issues.
        
           | nextworddev wrote:
           | Kinesis is decent
        
             | zdc1 wrote:
             | That's heartening to know. I find running Kafka less
             | pleasant.
        
           | hnlmorg wrote:
           | This. 100 times this.
        
           | jeffparsons wrote:
           | RDS, Route53, and Elasticache are decent, too. But yes, I've
           | also been bitten badly in the distant past by attempting to
           | rely on their higher-level services. I guess some things
           | don't change.
           | 
           | I wonder if the difference is stuff they dogfood versus stuff
           | they don't?
        
             | ozten wrote:
             | A big problem for a when three AWS teams launch the same
             | thing. Lowers confidence in dogfooding the "right" one.
        
           | belter wrote:
           | >But there are a lot of services they have that have some big
           | rough patches.
           | 
           | Enlight us...
        
       | ChrisArchitect wrote:
       | Amazon post:
       | https://www.aboutamazon.com/news/aws/trainium-3-ultraserver-...
        
       | cmiles8 wrote:
       | AWS keeps making grand statements about Trainium but not a single
       | customer comes on stage to say how amazing it is. Everyone I
       | talked to that tries it says there were too many headaches and
       | they moved on. AWS pushes it hard but "more price performant"
       | isn't a benefit if it's a major PITA to deploy and run relative
       | to other options. Chips without a quality developer experience
       | isn't gonna work.
       | 
       | Seems AWS is using this heavily internally, which makes sense,
       | but not observing it getting traction outside that. Glad to see
       | Amazon investing there though.
        
         | giancarlostoro wrote:
         | Not just AWS, looks like Anthropic uses it heavily as well. I
         | assume they get plenty of handholding from Amazon though. I'm
         | surprised any cloud provider does not invest drastically more
         | into their SDK and tooling, nobody will use your cloud if they
         | literally cannot.
        
           | cmiles8 wrote:
           | Well AWS says Anthropic uses it but Anthropic isn't exactly
           | jumping up and down telling everyone how awesome it is, which
           | tells you everything you need to know.
           | 
           | If Anthropic walked out on stage today and said how amazing
           | it was and how they're using it the announcement would have a
           | lot more weight. Instead... crickets from Anthropic in the
           | keynote
        
             | teruakohatu wrote:
             | > Anthropic isn't exactly jumping up and down telling
             | everyone how awesome it is, which tells you everything you
             | need to know.
             | 
             | You can't really read into that. They are unlikely to let
             | their competitors know if they have a slight performance/$
             | edge by going with AWS tech.
        
               | cmiles8 wrote:
               | With GCP announcing they built Gemini 3 on TPUs the
               | opposite is true. Anthropic is under pressure to show
               | they don't need expensive GPUs. They'd be catching up at
               | this point, not leaking some secret sauce. No reason for
               | them to not boast on stage today unless there's nothing
               | to boast about.
        
               | 0x457 wrote:
               | Yes, but Google benefit from people using their TPUs,
               | while Anthropic gains nothing unless AWS throws money at
               | them for saying it.
        
               | bilbo0s wrote:
               | This.
               | 
               | Anthropic is not going to interrupt their competitors if
               | their competitors don't want to use trainium. Neither
               | would you, I, nor anyone else. The only potential is
               | downside. There's no upside potential for them at all in
               | doing so.
               | 
               | From Anthropic's perspective, if the rest of us can't
               | figure out how to make trainium work? Good.
               | 
               | Amazon will fix the difficulty problem with time, but
               | that's time Anthropic can use to press their advantages
               | and entrench themselves in the market.
        
               | fishmicrowaver wrote:
               | Striking a deal with a competitor (AZURE) does though.
        
             | cobolcomesback wrote:
             | AWS has built 20 data centers in Indiana full of half a
             | million Trainium chips explicitly for Anthropic. Anthropic
             | is using them heavily. The same press announcement that
             | Anthropic has made about Google TPUs is the exact same one
             | they made a year ago about Trainium. Hell, even in the
             | Google TPU press release they explicitly mention how they
             | are still using Trainium as well.
        
               | VirusNewbie wrote:
               | Can you link to the press releases? The only one I'm
               | aware of by Anthropic says they _will_ use Tranium for
               | future LLMs, not that they _are_ using them.
        
               | cobolcomesback wrote:
               | This is the Anthropic press release from last year saying
               | they will use Trainium:
               | https://www.anthropic.com/news/anthropic-amazon-trainium
               | 
               | This is the AWS press release from last month saying
               | Anthropic _is_ using 500k Trainium chips and _will_ use
               | 500k more: https://finance.yahoo.com/news/amazon-says-
               | anthropic-will-us...
               | 
               | And this is the Anthropic press release from last month
               | saying they will use more Google TPUs but also are
               | continuing to use Trainium (see the last 2 paragraphs
               | specifically): https://www.anthropic.com/news/expanding-
               | our-use-of-google-c...
        
               | VirusNewbie wrote:
               | There is no press release saying that they are using 500k
               | trainium chips. You can search on amazon's site.
        
           | IshKebab wrote:
           | > I'm surprised any cloud provider does not invest
           | drastically more into their SDK and tooling
           | 
           | I used to work for an AI startup. This is where Nvidia's moat
           | is - the tens of thousands of man-hours that has gone into
           | making the entire AI ecosystem work well with Nvidia hardware
           | and not much else.
           | 
           | It's not that they haven't thought of this, it's just that
           | they don't want to hire another 1k engineers to do it.
        
           | logicchains wrote:
           | >I'm surprised any cloud provider does not invest drastically
           | more into their SDK and tooling, nobody will use your cloud
           | if they literally cannot.
           | 
           | Building an efficient compiler from high-level ML code to a
           | TPU is actually quite a difficult software engineering feat,
           | and it's not clear that Amazon has the kind of engineering
           | talent needed to build something like that. Not like Google
           | which have developed multiple compilers and language
           | runtimes.
        
         | phamilton wrote:
         | The inf1/inf2 spot instances are so unpopular that they cost
         | less than the equivalent cpu instances. Exact same (or better)
         | hardware but 10-20% cheaper.
         | 
         | We're not quite seeing that on the trn1 instances yet, so
         | someone is using them.
        
           | kcb wrote:
           | Heh, I was looking at an eks cluster recently that was using
           | Cast AI autoscalar. Scratching my head as there was a bunch
           | of inf instances. Then I realized it must be cheap spot
           | pricing.
        
       | jauntywundrkind wrote:
       | Amazon aside, interesting future here with NVLink getting more
       | and more folks using it. Intel is also onboard with NVlink. This
       | is like an PCI -> AGP moment, but Nvidia's AGP.
       | 
       | AMD felt like they were so close to nabbing the accelerator
       | future back in HyperTransport days. But the recent version
       | Infinity Fabric is all internal.
       | 
       | There's Ultra Accelerator Link (UALink) getting some steam.
       | Hypothetically CXL should be good for uses like this, using PCIe
       | PHY but lower latency lighter weight; close to ram latency, not
       | bad! But still a mere PCIe speed, not nearly enough, with PCIe
       | 6.0 just barely emerging now. Ideally IMO we'd also see more
       | chips come with integrated networking too: it was so amazing when
       | Intel Xeon's had 100Gb Omni-Path for barely any price bump.
       | UltraEthernet feels like it should be on core, gratis.
        
         | wmf wrote:
         | NVLink Fusion sounds like a total trap where you pay to become
         | Jensen's slave. It may make sense for Intel because they're
         | desperate. It's not a good look for AWS to put themselves in
         | the same category.
         | 
         |  _UltraEthernet feels like it should be on core, gratis._
         | 
         | I've been saying for a while that AMD should put a SolarFlare
         | NIC in their I/O die. They already have switchable PCIe/SATA
         | ports, why not switchable PCIe/Ethernet? UEC might be too niche
         | though.
        
       | mlmonkey wrote:
       | Not a single mention of any benchmarks or performance.
        
         | pedalpete wrote:
         | They say 4x more, but not 4x faster, 4x more memory, but not 4x
         | more than what!?
        
       | landl0rd wrote:
       | Anyone considering using trainium should view this Completely
       | Factual Infomercial:
       | https://x.com/typedfemale/status/1945912359027114310
       | 
       | Pretty accurate in my experience, especially re: the neuron sdk.
       | Do not use.
        
       | deepsquirrelnet wrote:
       | Heavens to Betsy, I don't know if you can hear me, But try
       | supporting these things if you actually want them to be
       | successful. About the 3rd day into trying to roll your own LMI
       | container in sagemaker because they haven't updated the vLLM
       | version in 6 months and you can't run a regular sagemaker
       | endpoint because of a ridiculous 60s timeout that was determined
       | to be adequate 8 years ago. I can only imagine the hell that
       | awaits the developer that decides to try their custom silicon.
        
       ___________________________________________________________________
       (page generated 2025-12-02 23:00 UTC)