| 1. | | Show HN: self-adaptive cluster for LLM inference (rivvr.ai) |
| | predicted 7 points by anon | 0 comments |
|
| 2. | | Show HN: Making LLM run 10x cheaper |
| | predicted 7 points by anon | 0 comments |
|
| 3. | | Show HN: does llm lie? |
| | predicted 3 points by anon | 0 comments |
|
| 4. | | Passport rankings are wrong. They count Tuvalu the same as France. (aiandtractors.com) |
| | predicted 2 points by anon | 0 comments |
|
| 5. | | Reducing image asset size by 45% (github.com) |
| | predicted 44 points by anon | 0 comments |
|
| 6. | | Show HN: 3x cheaper, 2x faster, 0% performance loss LLM inference |
| | predicted 8 points by anon | 0 comments |
|
| 7. | | Show HN: making LLMs run 3x cheaper |
| | predicted 7 points by anon | 0 comments |
|
| 8. | | Show HN: same latency, 70% cheaper LLM inference |
| | predicted 7 points by anon | 0 comments |
|
| 9. | | Show HN: Run LLMs with predictable SLO and economy |
| | predicted 4 points by anon | 0 comments |
|
| 10. | | Show HN: We managed to run LLMs 60% cheaper |
| | predicted 7 points by anon | 0 comments |
|
| 11. | | Show HN: Auto-optimized LLM Inference for SLO and economy |
| | predicted 3 points by anon | 0 comments |
|
| 12. | | I building agent with own cloud to solve any task (ardor.cloud) |
| | predicted 2 points by anon | 0 comments |
|
| 13. | | Show HN: Rivvr - LLM Inference Autopilot for AWS |
| | predicted 3 points by anon | 0 comments |
|
| 14. | | Show HN: Fairvisor — rate limits for APIs without a shared store |
| | predicted 7 points by anon | 0 comments |
|
| 15. | | Show HN: Fairvisor — rate limits without global state |
| | predicted 5 points by anon | 0 comments |
|
| 16. | | Show HN: Fairvisor — rate limits without a shared counter |
| | predicted 6 points by anon | 0 comments |
|
| 17. | | Show HN: Fairvisor — rate limits for APIs without a global counter |
| | predicted 6 points by anon | 0 comments |
|
| 18. | | Show HN: Fairvisor — rate limits for APIs without a distributed counter |
| | predicted 7 points by anon | 0 comments |
|
| 19. | | Show HN: Fairvisor — rate limits for APIs without a shared counter |
| | predicted 7 points by anon | 0 comments |
|
| 20. | | Show HN: Fairvisor — rate limits for APIs without a central counter |
| | predicted 7 points by anon | 0 comments |
|
| 21. | | Show HN: Fairvisor — fair API limits without global state |
| | predicted 5 points by anon | 0 comments |
|
| 22. | | Show HN: Fairvisor — request limits for APIs without global state |
| | predicted 6 points by anon | 0 comments |
|
| 23. | | Show HN: Fairvisor — traffic limits for APIs without a global coordinator |
| | predicted 6 points by anon | 0 comments |
|
| 24. | | Show HN: Fairvisor — traffic limits for APIs without global state |
| | predicted 6 points by anon | 0 comments |
|
| 25. | | Show HN: Fairvisor — rate limiting for APIs without global state |
| | predicted 6 points by anon | 0 comments |
|
| 26. | | Show HN: Fairvisor — traffic control for APIs without global state |
| | predicted 6 points by anon | 0 comments |
|
| 27. | | Show HN: Fairvisor — traffic control for APIs without a shared counter |
| | predicted 7 points by anon | 0 comments |
|
| 28. | | Show HN: Fairvisor — traffic control for APIs, locally |
| | predicted 5 points by anon | 0 comments |
|
| 29. | | Show HN: Fairvisor — local traffic control for APIs |
| | predicted 5 points by anon | 0 comments |
|
| 30. | | Show HN: Fairvisor — a single policy for API limits |
| | predicted 4 points by anon | 0 comments |
|