Arkaprava Basu
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Ajay Nayak2×
- Abhishek Ghoshonce
- Ashish Panwaronce
all 8 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| GraCE: Unlocking CUDA Graphs with Compiler Support for ML Workloads | 20th USENIX Symposium on Operating Systems Design and Implementation (OSDI '26) | 2026-07-13 |
GraCE is a compiler framework built atop PyTorch2 that unlocks CUDA Graphs for 25 ML workloads (TorchBench, HuggingFace, TIMM) and requires no code changes. It… | ||
| HyCache: Hybrid Caching for Accelerating DNN Input Preprocessing Pipelines | USENIX ATC '25 | 2025-07-07 |
Hybrid Cache automatically profiles ~1% of a dataset, models fetch/decode/augment costs, and uses an ILP solver to pick per-stage, tier-aware placements that… | ||
| Faastlane: Accelerating Function-as-a-Service Workflows | USENIX ATC '21 | 2021-07-14 |
Faastlane runs workflow functions as threads within a single process (on Apache OpenWhisk) so intermediate data travels by loads/stores instead of network or… | ||
| nothing matches | ||