| | Host overhead is killing your inference efficiency (modal.com) |
| 1 point by ronfriedhaber 47 days ago | past |
|
| | Kimi K3 by Moonshot now available on Modal (modal.com) |
| 4 points by yogthos 49 days ago | past |
|
| | What Is Flash Attention? (modal.com) |
| 2 points by ronfriedhaber 49 days ago | past |
|
| | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 1 point by birdculture 54 days ago | past |
|
| | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 4 points by birdculture 56 days ago | past | 1 comment |
|
| | Scaling to 1M concurrent sandboxes in seconds (modal.com) |
| 76 points by thundergolfer 61 days ago | past | 15 comments |
|
| | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 1 point by birdculture 70 days ago | past |
|
| | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 2 points by birdculture 73 days ago | past |
|
| | Proxying inference requests in 6ms with Pingora, Envoy, and Spanner (modal.com) |
| 2 points by birdculture 77 days ago | past |
|
| | Speculation is all you need (modal.com) |
| 2 points by zachperkel 77 days ago | past |
|
| | Routing for serverless servers with Pingora, Envoy, and Spanner (modal.com) |
| 2 points by birdculture 81 days ago | past |
|
| | Routing for serverless servers with Pingora, Envoy, and Spanner (modal.com) |
| 11 points by charles_irl 82 days ago | past |
|
| | Modal Auto Endpoints: Optimized inference you own (modal.com) |
| 19 points by handfuloflight 84 days ago | past | 4 comments |
|
| | Speculation Is All You Need (modal.com) |
| 5 points by birdculture 85 days ago | past |
|
| | Unpacking sandbox startup latency: why started ≠ ready (modal.com) |
| 4 points by heygarrison 85 days ago | past | 1 comment |
|
| | Speculation Is All You Need (modal.com) |
| 4 points by birdculture 86 days ago | past |
|
| | Speculation Is All You Need (modal.com) |
| 3 points by birdculture 87 days ago | past |
|
| | Speculation Is All You Need (modal.com) |
| 12 points by charles_irl 88 days ago | past |
|
| | Making FlashAttention-4 faster for inference (modal.com) |
| 2 points by birdculture 3 months ago | past |
|
| | Making FlashAttention-4 faster for inference (modal.com) |
| 4 points by birdculture 3 months ago | past |
|
| | Making FlashAttention-4 faster for inference (modal.com) |
| 3 points by birdculture 3 months ago | past |
|
| | Making FlashAttention-4 faster for inference (modal.com) |
| 2 points by matt_d 3 months ago | past |
|
| | Modal Major Outage (modal.com) |
| 4 points by hunkins 3 months ago | past | 2 comments |
|
| | Modal's Series C: Raising $355M at a $4.65B valuation (modal.com) |
| 2 points by yla92 3 months ago | past |
|
| | Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint (modal.com) |
| 91 points by charles_irl 4 months ago | past | 18 comments |
|
| | How to Achieve Truly Serverless GPUs (modal.com) |
| 1 point by birdculture 4 months ago | past |
|
| | How to Achieve Serverless GPUs (modal.com) |
| 4 points by gmays 4 months ago | past |
|
| | How to Achieve Truly Serverless GPUs (modal.com) |
| 2 points by birdculture 4 months ago | past |
|
| | How to Achieve Truly Serverless GPUs (modal.com) |
| 3 points by birdculture 4 months ago | past |
|
| | How to Achieve Serverless GPUs (modal.com) |
| 8 points by charles_irl 4 months ago | past |
|
|
| More |
