►
From YouTube: 005 ONNX 20211021 Huang ONNX and Ascend CANN inference interoperability for better performance
Description
LF AI & Data Day - ONNX Community Day, October 21, 2021
Ascend CANN and ONNX : inference interoperability for better performance
Speaker: Zhipeng Huang (Huawei)
A
So,
first
of
all,
just
a
brief
memory.
Lane
of
what
is
open
source
participation
in
onyx.
A
We
actually
have
been
working
with
onyx
community,
with
the
china
workshop
and
from
the
very
start
dating
back
almost
four
years
ago,
and
we
have
been
participating
at
each
and
every
onex
workshop,
whether
it's
on
online
or
offline,
as
many
as
possible
in
the
community.
We
have
spirit
headed
the
ash
working
group
initiative.
We
proposed
the
onyx
edge
runtime
architecture,
so,
starting
last
year,
mine
sport
mindsport,
which
is
our
latest
deep
learning,
training
and
inference
framework,
has
has
been
using
onyx
in
a
large
scale.
A
And
today
I'm
gonna
talk
about
our
hardware
support
for
onyx,
and
this
is
what
also
this
pr
is
about.
A
So,
as
you
can
see
from
the
figure
on
the
left
hand,
in
canon,
we
have
the
acl
for
the
overall
api.
We
we
use
ecl
for
the
unified
application,
programming,
interface
and
lower
down.
We
have
the
unified
neural
network
graph
construction
interfaces,
which
is
air
as
a
standardized
intermediate
representation,
and
we
have
a
very
high
performance,
compute
engine
and
operator
libraries,
and
we
have
a
a
base
service
layer
which
provide
capabilities
like
the
drivers,
virtualization
communications
and
so
forth.
A
So
in
our
latest
release
the
can
5.0
we
currently
have
supported
more
than
140
onyx
inference
models,
and
hopefully
that
number
will
reach
to
more
than
200
by
the
end
of
the
year.
A
Can
5.0
support
offset
8
to
13
with
the
offset
element
as
the
the
key
offset
we
can
support
and
more
than
90
of
the
ops
will
be
supported
on
camp
by
the
end
of
the
year
and
from
figure
you
can
see
from
the
5.0
version
to
the
earlier
3.0
version.
We
have
a
dramatic
increase
of
performance
and
you
are
more
than
welcome
to
check
out
our
moto
zoo
and
check
out
the
onyx
models.
We
have
been
building
upon
a
cent
chem.
A
So
here
are
some
future
thoughts.
There
are
a
couple
of
pinpoints
that
we
have
identified
during
our
line
of
work,
and
hopefully
the
community
will
address
these
issues
in
the
near
future.
A
The
seventh
problem
we
identified
is
that
the
the
iteration
of
onyx
offset
is
very
fast.
On
the
one
hand,
it's
a
good
thing.
It
represents
the
fast
development
pace
of
on
its
community,
but
it
also
creates
difficulties
for
hardware
engineers,
like
the
can
developers
to
do
the
onyx
adaptation
work.
A
Okay
here
here
is
the
end
of
my
topic.
You
are
more
than
welcome
to
check
out
a
zen.
Can
we
have
repos
on
gt
and
also
on
gita?
Please
also
feel
free
to
reach
out
to
me
if
you've
got
any
questions.
Thank
you
very
much.