| user: | OsamaJaber |
| created: | October 19, 2025 |
| karma: | 264 |
| 1. | |
| 2. | GLM 5.3 Flash faster and cheaper(runinfra.ai) |
| 3. | The fastest and cheapest GLM 5.3 Flash endpoint(runinfra.ai) |
| 4. | |
| 5. | Fastest Inference in MENA(runinfra.ai) |
| 6. | |
| 7. | |
| 8. | |
| 9. | Kimi K3 2.78T on One CPU with 8GB RAM(github.com) |
| 10. | |
| 11. | Lossless Inference(runinfra.ai) |
| 12. | DeepSeek V4 Flash 2.98x faster, lossless(runinfra.ai) |
| 13. | DeepSeek-V4-Flash 2.98x faster on 4x B200, lossless(twitter.com) |
| 14. | |
| 15. | |
| 16. | What LLM Inference Costs(twitter.com) |
| 17. | Kimi k3 run on RTX 5090(github.com) |
| 18. | Kimi k3 now runs on one consumer GPU(twitter.com) |
| 19. | The AGI Compiler "Auto"(github.com) |
| 20. | Compiler for LLMs, world models, and AGI(arxiv.org) |