Etched ✓
@Etched · San Jose · joined 21 Apr 2024
Frontier Inference Clusters
60 993Followers
3Following
50Posts total
25.8MViews on collected posts
Ultimi post
Cerchiamo nuovi post…
@Etched I see you spent a lot of investor money on a video shoot, but there's very little details. What's in the rack? I know it's not your chip. Is it NVIDIA chips? Are there any chips at all?
45.4K views · 474 likes
· 5 reposts · 18 replies
Open on X →
If you're excited to tackle the challenges required to run the world's inference like:
- Building a Gigawatt-scale factory
- Orchestrating quadrillion-token clusters
- Making self-improving kernel agents
- Designing new product lines from scratch
You should join us:
91.2K views · 218 likes
· 7 reposts · 5 replies
Open on X →
We're grateful for our customers, suppliers, and investors for enabling us to ramp production.
Under 1% of the world has access to frontier models. Scaling intelligence requires a new kind of inference hardware.
Our mission has never been more urgent.
https://t.co/c3yqyajGpf
120.8K views · 275 likes
· 9 reposts · 4 replies
Open on X →
Before leading the round, Jane Street tested our hardware. In their words:
“We tested the chip and are pleased with the early results. Etched’s unique approach to inference delivers the precision we will need to support our most demanding workloads.” https://t.co/DPmlJCcPyb
262.4K views · 513 likes
· 13 reposts · 6 replies
Open on X →
We've raised $700M at a $21B valuation from Jane Street, Kleiner Perkins, Sequoia, A16Z, Peter Thiel, BCV, and Blackstone.
We're also excited to share that we've shipped our first rack to Jane Street. https://t.co/MFlF2xSw0B
7.8M views · 7K likes
· 454 reposts · 302 replies
Open on X →
0:09
@Etched If Jane street is in just know that shit is going to the moon
8.5K views · 70 likes
· 0 reposts · 1 replies
Open on X →
Firmware at Etched builds the software that controls our inference clusters.
That means custom algorithms and schemas to achieve maximum performance: doorbell-free submission paths, high-speed swapping to live spares, and nanosecond-accurate profiling tools.
Firmware co-designs
54.4K views · 87 likes
· 1 reposts · 1 replies
Open on X →
Chip design is what connects our inference system.
Our entire silicon flow is custom for inference. We develop critical IP in-house, including our fabrics, interconnects, math blocks, and memories.
Closing blocks at low voltages is a very hard PD problem. Etched heavily invests
55.7K views · 95 likes
· 3 reposts · 2 replies
Open on X →
We're hiring across inference, firmware, platform, chip design, and more.
We believe in end-to-end ownership that spans beyond most engineering roles.
We look for people that are deeply curious to understand the entire inference system, often beyond what's comfortable.
148.5K views · 258 likes
· 4 reposts · 4 replies
Open on X →
Electrical engineering at Etched is uniquely challenging.
Enabling low-voltage inference and cluster-scale memory requires breakthroughs across our platform.
Our PCBs handle tons of current and high-speed SerDes while being manufacturable at scale. This means asymmetric PCB
72.4K views · 117 likes
· 3 reposts · 1 replies
Open on X →
Inference at Etched is much more than writing kernels. We own the full stack, from KV cache management to sharding algorithms to workload-aware SerDes tuning.
We push the Pareto curve daily, co-design models with customers, collaborate with chip designers, and are always
100.4K views · 187 likes
· 6 reposts · 4 replies
Open on X →
We’ve raised $300M in Series C funding at a $10.3B valuation from Sequoia, Andreessen Horowitz, Jane Street, Argo, and SK Hynix.
Our mission is to run the world's inference. This round accelerates production of our inference clusters.
We've opened an 80,000-sqft, 10-MW facility
7.5M views · 5.6K likes
· 355 reposts · 183 replies
Open on X →
We're grateful for the support from our partners, suppliers, and team. We have a lot of work to do as we ramp production.
https://t.co/icKP5locmY
259.1K views · 328 likes
· 3 reposts · 5 replies
Open on X →
@Etched @UbertiGavin @robertwachen Gavin is smart, needs to learn how to communicate like a person. His cadence, swaying, voice inflections are tough to listen to
511 views · 2 likes
· 0 reposts · 0 replies
Open on X →
@Etched @UbertiGavin @robertwachen Incredible pod, had a lot of fun with this one!
1K views · 9 likes
· 0 reposts · 0 replies
Open on X →
Vertically integrating the full inference hardware stack is extremely hard.
Hear @UbertiGavin and @robertwachen share three years of battle stories leading into today's launch
https://t.co/1x7EwtB2Qm
288.5K views · 605 likes
· 60 reposts · 25 replies
Open on X →
@Etched Congrats!! I was impressed to learn about some of the engineering wizardry (e.g. *very* low voltage domains, cluster scale memory, ...) that goes into tokens/watt maxxing of state of the art LLMs at interactive tokens/sec/user. Esp fun and memorable is the idea that this
108.6K views · 1.7K likes
· 45 reposts · 25 replies
Open on X →
We're scaling production as fast as possible.
We built a 2MW datacenter in our office and opened a Taiwan factory for 24/7 engineering.
Performance, roadmap, and more updates are coming this summer.
If this excites you, join us to build the future of gigawatt-scale inference:
130.8K views · 684 likes
· 13 reposts · 9 replies
Open on X →
Introducing Cluster-Scale Memory (CSM) for low latency workloads.
Today's AI chips using HBM can’t achieve SRAM-level decode speeds due to memory subsystem and interconnect bottlenecks. SRAM-only chips have lower FLOPs density and memory capacity, sacrificing throughput.
You’re
535.7K views · 991 likes
· 53 reposts · 16 replies
Open on X →
Introducing Low-Voltage Inference (LVI) for high throughput workloads.
Today, AI chips can't scale FLOPs without thermal throttling.
As FLOPs utilization increases, AI chips draw more power and downregulate clock speed. This often results in sustained inference throughput under
513.8K views · 1.3K likes
· 69 reposts · 19 replies
Open on X →
Our inference systems are built to push the entire pareto curve on frontier models, including many-trillion parameter MoEs, long context, and agentic workloads.
We've co-designed new chips, packages, PCBs, cold plates, interconnects, & more.
Today, we're sharing two
125.9K views · 476 likes
· 11 reposts · 4 replies
Open on X →
We're grateful to be backed by the world's best researchers and founders, including:
@geoffreyhinton @peterthiel @karpathy @polynoamial @ScottWu46 @tri_dao @spectorb @MillionInt @ZachBDell @talbroda @IrwanBello @nikesharora @zoink @drfeifei @arthurmensch @aidangomez @amasad
149.9K views · 687 likes
· 10 reposts · 9 replies
Open on X →
We're a team of 400+ engineers from NVIDIA, TPUs, Broadcom, SK Hynix, TSMC, & more.
We're backed by Jane Street, HRT, Two Sigma, and Jump, with strategic investment from VentureTech Alliance. We're excited to deepen our partnership with the world's leading fab.
Our Series B was
183.2K views · 1.3K likes
· 37 reposts · 6 replies
Open on X →
We're coming out of stealth.
We've built our first racks after a successful A0 tapeout, $1B+ in customer contracts, and $800m raised.
Early customer tests show us achieving SOTA throughput, latency, and power efficiency on inference workloads.
Our first racks ship this summer.
6.8M views · 9.9K likes
· 959 reposts · 651 replies
Open on X →
We're excited to partner with @Cognition_Labs @mercor @CoreWeave and @AnthropicAI to host an inference-time compute hackathon, featuring >$60K in cash prizes and >1 exaflop of free compute. https://t.co/eKRBk03r0b
145.4K views · 355 likes
· 24 reposts · 9 replies
Open on X →
Rispetto ad account della stessa dimensione
6 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. arriva a molti, ma pochi di loro reagiscono.
Visualizzazioni mediane106 022questo account924mediana per 10K–100K
Copertura, %173.83%questo account3.62%mediana per 10K–100K
Interazione, %0.23%questo account1.52%mediana per 10K–100K
| Metrica | Questo account | Mediana per 10K–100K | Rapporto |
|---|---|---|---|
| Visualizzazioni mediane per post | 106 022 | 924 | 115× |
| Copertura (visualizzazioni ÷ follower) | 173.83% | 3.62% | 48.0× |
| Tasso di interazione | 0.23% | 1.52% | 0.15× |
Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
7.5M23 Jul
100.4K
72.4K
148.5K
55.7K
48.5K
54.4K
8.5K
7.8M18 Aug
262.4K
120.8K
91.2K
66.7K
45.4K
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.08%23 Jul
0.20%
0.17%
0.18%
0.18%
0.18%
0.16%
0.84%
0.10%18 Aug
0.21%
0.24%
0.25%
0.23%
1.11%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes68.9%34 063 in total
Reposts4.4%2 163 in total
Replies2.7%1 332 in total
Quotes2.8%1 397 in total
Bookmarks21.2%10 469 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Account simili
Miquel Iceta Llorens /🌹🇺🇳
@miqueliceta
122K followers
· 133.1K posts
Héctor de León (El loco de los perros) ⛧
@powerhdeleon
122K followers
· 110.7K posts
Christopher Hope📝 ✓
@christopherhope
122K followers
· 58.2K posts
Diamond Media ✓
@diamondtvzambia
122K followers
· 43.5K posts
☭ Locura González ✓
@padrura
122K followers
· 26.2K posts
ふあえ@FANBOX ✓
@lucien_000298
122K followers
· 1.2K posts
fwee(フィー) 日本公式 ✓
@fwee_makeup_jp
122K followers
· 1.8K posts
Iowa Women's Basketball ✓
@IowaWBB
122K followers
· 27.9K posts
Frequently asked questions about @Etched
How many followers does @Etched have?
60 993 followers.
How many posts has @Etched published?
50 posts.
How do posts by @Etched perform?
Collected posts: 29. Views: 25 793 887. Likes: 34 063.