asplos'23 - session 7a - optimus-cc: efficient large nlp model training with 3d parallelism aware co
Published 1 year ago • 206 plays • Length 13:15Download video MP4
Download video MP3
Similar videos
-
13:34
asplos'23 - session 7a - dpacs: hardware accelerated dynamic neural network pruning through algorith
-
12:00
asplos'23 - session 7a - deepum: tensor migration and prefetching in unified memory
-
13:03
asplos'23 - session 7a - hyperscale hardware optimized neural architecture search
-
13:46
asplos'22 - session 7a - faasflow: enable efficient workflow execution for function-as-a-service
-
10:55
asplos'23 - session 7a - lucid: a non-intrusive, scalable and interpretable scheduler for deep learn
-
12:13
asplos'23 - session 7b - finding unstable code via compiler-driven differential testing
-
1:26
asplos'24 - lightning talks - session 7a - cmc: video transformer acceleration via codec assisted ma
-
18:25
porting onnc to nvdla
-
16:54
asplos'20 - session 3b - why gpus are slow at executing nfas and how to make them faster
-
11:35
asplos'23 - session 5b - prism: optimizing key-value store for modern heterogeneous storage devices
-
10:53
asplos'23 - session 4a - ehdl: turning ebpf/xdp programs into hardware designs for the nic
-
12:39
asplos'23 - session 7b - characterizing and optimizing end-to-end systems for private inference
-
12:02
asplos'23 - session 1c - sti: turbocharge nlp inference at the edge via elastic pipelining
-
18:05
asplos'22 - session 1a - bison-e: a lightweight and high-performance accelerator for narrow integer
-
11:49
asplos'23 - session 7c - vdom: fast and unlimited virtual domains on multiple architectures
-
10:33
asplos'23 - session 5c - tlp: a deep learning-based cost model for tensor program tuning
-
11:25
asplos'23 - session 1a - heron: automatically constrained high-performance library generation for de