| 1. | | RL on mixed-precision, mixed-accelerator samplers (modal.com) |
| 1 point by birdculture 22 days ago | past |
|
| 2. | | Fast Filesystems for VMs (modal.com) |
| 1 point by birdculture 23 days ago | past |
|
| 3. | | Toward RL on mixed-precision, mixed-accelerator samplers (modal.com) |
| 1 point by birdculture 25 days ago | past |
|
| 4. | | Building Fast Filesystems for VMs (modal.com) |
| 3 points by birdculture 26 days ago | past |
|
| 5. | | Toward RL on mixed-precision, mixed-accelerator samplers (modal.com) |
| 1 point by birdculture 27 days ago | past |
|
| 6. | | Building Fast Filesystems for VMs (modal.com) |
| 11 points by amitprasad 28 days ago | past |
|
| 7. | | Toward RL on mixed-precision, mixed-accelerator samplers (modal.com) |
| 2 points by torutofu 28 days ago | past |
|
| 8. | | Modal crosses $1B in Annualized Run Rate and raises $750M Series D (modal.com) |
| 4 points by zachthewf 30 days ago | past |
|
| 9. | | How to serve trillions of tokens for trillion-parameter coding agents (modal.com) |
| 2 points by birdculture 44 days ago | past |
|
| 10. | | Hitting 1B tokens/minute on 1 GPU combining a query planner and inference engine (modal.com) |
| 2 points by gmays 44 days ago | past |
|
| 11. | | Quail: Speed up AI-SQL by jointly optimizing query planner and inference engine (modal.com) |
| 3 points by charles_irl 45 days ago | past |
|
| 12. | | GPU Glossary (modal.com) |
| 2 points by ibobev 46 days ago | past |
|
| 13. | | GPU Glossary (Readable) (modal.com) |
| 2 points by gtsnexp 47 days ago | past |
|
| 14. | | GPU Glossary (modal.com) |
| 4 points by sonabinu 47 days ago | past |
|
| 15. | | >1B tokens/minute/GPU by combining query planner and inference engine (modal.com) |
| 1 point by birdculture 47 days ago | past |
|
| 16. | | >1B tokens/minute/GPU by combining query planner and inference engine (modal.com) |
| 7 points by charles_irl 48 days ago | past | 2 comments |
|
| 17. | | How to serve trillions of tokens for trillion-parameter coding agents (modal.com) |
| 4 points by birdculture 48 days ago | past |
|
| 18. | | How to serve trillions of tokens for trillion-parameter coding agents (modal.com) |
| 2 points by birdculture 50 days ago | past |
|
| 19. | | How to serve trillions of tokens for trillion-parameter coding agents (modal.com) |
| 2 points by charles_irl 50 days ago | past |
|
| 20. | | How to serve trillions of tokens for trillion-parameter coding agents (modal.com) |
| 1 point by kkm 51 days ago | past |
|
| 21. | | Host overhead is killing your inference efficiency (modal.com) |
| 1 point by ronfriedhaber 3 months ago | past |
|
| 22. | | Kimi K3 by Moonshot now available on Modal (modal.com) |
| 4 points by yogthos 3 months ago | past |
|
| 23. | | What Is Flash Attention? (modal.com) |
| 2 points by ronfriedhaber 3 months ago | past |
|
| 24. | | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 1 point by birdculture 3 months ago | past |
|
| 25. | | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 4 points by birdculture 3 months ago | past | 1 comment |
|
| 26. | | Scaling to 1M concurrent sandboxes in seconds (modal.com) |
| 76 points by thundergolfer 4 months ago | past | 15 comments |
|
| 27. | | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 1 point by birdculture 4 months ago | past |
|
| 28. | | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 2 points by birdculture 4 months ago | past |
|
| 29. | | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 2 points by birdculture 4 months ago | past |
|
| 30. | | Speculation is all you need (modal.com) |
| 2 points by zachperkel 4 months ago | past |
|
|
| More |
