How OneTriangle launched on X
Posted Nov 16, 2026 by @hannah_chuuEngagement read Nov 17, 2026
Today we’re launching cross-model KV cache transfer from @OneTriangle, a step towards efficient model communication. Up to 10.8x faster TTFT at 1M context. Prefill small model, transfer KV cache, decode on large. SDK live for Qwen3.5-4B → Qwen3.8-27B, beta open for more model pairs.
- 460
- Likes
- 38
- Reposts
- 56
- Replies
- 12
- Quotes
- 374
- Bookmarks
How EPTA rated the launch
- Hook
- Editing / Creativity
- Copy
- Sentiment of launch
- Distribution strategy
How it compares
| Group | Launches | Median views | This one | Rank |
|---|---|---|---|---|
| AI infrastructure and chips launches | 127 | 187.1K | 0.15x | #119 / 127 |
| Product launchs | 513 | 125.8K | 0.23x | #460 / 513 |
| Accounts with 1K to 10K followers | 400 | 150.5K | 0.19x | #363 / 400 |
| Every launch | 963 | 147.7K | 0.19x | #880 / 963 |
What the numbers say
132 of every 10,000 viewers bookmarked it, above the directory median of 17. Bookmarks are the clearest sign a launch was worth coming back to.
The video runs 0:08, shorter than the median launch video at 0:53.
The post is 284 characters, shorter than the median launch post at 302.
It went out on a Monday. Launches posted on Mondays have a median of 140K views; Fridays lead at 235.5K.
Comparable launches
2026-11-17 · Source: EPTA launch directory, epta.co/directory. Free to use with attribution (CC BY 4.0).