issues
search
SJTU-IPADS
/
reef
REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.
Apache License 2.0
81
stars
6
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
non-idempotent kernels discussion
#9
utkusaglm
closed
5 months ago
2
对hipResetWavefronts有点迷糊
#8
lovelydett
closed
1 year ago
4
REEF for NVIDIA GPUs
#7
anakli
opened
1 year ago
11
what should I do for porting?
#6
gofreelee
opened
1 year ago
1
The result of the model does not match the pytorch output
#5
husterdjx
opened
1 year ago
1
Problems with the description of block scheduling in the paper
#4
five12
opened
1 year ago
1
The specific json file cannot get from official tvm
#3
husterdjx
closed
1 year ago
6
Why preempt reset the GPU need to execute `be_stream_device_queue_cap` times?
#2
flyflypeng
closed
1 year ago
4
How do I get the source code from the TVM model?
#1
battleonthebridge
closed
1 year ago
3