| | Tracing a Full MoE Training Step Through the XLA Compiler (patricktoulme.substack.com) |
| 3 points by matt_d 21 days ago | past |
|
| | CuTile on Blackwell: NVIDIA's Compiler Moat Is Already Built (patricktoulme.substack.com) |
| 3 points by matt_d 3 months ago | past |
|
| | When XLA Isn't Enough: From Pallas to VLIW with Splash Attention on TPU (patricktoulme.substack.com) |
| 1 point by matt_d 3 months ago | past |
|
| | When XLA Isn't Enough: From Pallas to VLIW with Splash Attention on TPU (patricktoulme.substack.com) |
| 1 point by patrick_toulme 3 months ago | past |
|
| | From Jax to VLIW: Tracing a Computation Through the TPU Compiler Stack (patricktoulme.substack.com) |
| 1 point by EvgeniyZh 3 months ago | past |
|
| | From Jax to VLIW: Tracing a Computation Through the TPU Compiler Stack (patricktoulme.substack.com) |
| 10 points by mario1870 4 months ago | past | 4 comments |
|
