Haojun Xia
where else to find them
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
all 15 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Quant-LLM: Accelerating the Serving of Large Language Models via FP6-Centric... | USENIX ATC 2024 | 2024-07-10 |
Quant-LLM demonstrates that FP6 weight quantization preserves LLM quality while enabling much cheaper serving by building a CUDA kernel suite called TC-FPx… | ||
| MonoNN: Enabling a New Monolithic Optimization Space for Neural Network Inference... | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
MonoNN compiles an entire static neural network into a monolithic kernel on a single GPU to slash CPU-to-GPU launch and off‑chip traffic, empirically… | ||
| nothing matches | ||