Megvii Engine Team
|
150a6a6151
|
perf(dispatch/trace): remove unnecessary h2d for constant
GitOrigin-RevId: d00de3fc1f
|
3 years ago |
Megvii Engine Team
|
81d8c73a41
|
perf(dispatch/trace): serval tricks to speed up trace
GitOrigin-RevId: 2bdd70cde2
|
3 years ago |
Megvii Engine Team
|
4fa6162027
|
perf(dispatch): improve performance of dispatch system
GitOrigin-RevId: 860028e1af
|
3 years ago |
Megvii Engine Team
|
ca00177719
|
perf(dispatch): speed up dispatch system
GitOrigin-RevId: eabbe3e021
|
3 years ago |
Megvii Engine Team
|
187c1dc081
|
fix(jit): copy aux var when shallow copying JITExecutor
GitOrigin-RevId: 3b331e1c17
|
3 years ago |
Megvii Engine Team
|
7bd848ce04
|
fix(subgraph): fix hand-written backward for serval jit-elemwise ops
GitOrigin-RevId: ea3a40d96e
|
3 years ago |
Megvii Engine Team
|
7be7656c9f
|
fix(imperative): explicitly manage global structures
GitOrigin-RevId: 0f910c34b6
|
3 years ago |
Megvii Engine Team
|
62034fb262
|
fix(imperative): make CompNode finalize happens before global object destructor
GitOrigin-RevId: 9a1f507c69
|
3 years ago |
Megvii Engine Team
|
59cbf9583d
|
fix(subgraph): use CompiledOp in cpu to avoid workspace error
GitOrigin-RevId: 104dd982ef
|
3 years ago |
Megvii Engine Team
|
b6ce02a152
|
fix(subgraph): fallback back to cg if jit unsupported
GitOrigin-RevId: 853a00a402
|
3 years ago |
Megvii Engine Team
|
21f5a7fcc0
|
fix(subgraph): fix device recognition and scalar propagate
GitOrigin-RevId: fd2fe8bec9
|
3 years ago |
Megvii Engine Team
|
27346b0b65
|
test(opr): add scalar check for opr_test
GitOrigin-RevId: dcfd7ad5d6
|
3 years ago |
Megvii Engine Team
|
225045236b
|
perf(imperative): improve shape inference
GitOrigin-RevId: 98b4d7e9af
|
3 years ago |
Megvii Engine Team
|
df3474ca1d
|
perf(functional): rewrite serval elemwise ops with jit subgraph
GitOrigin-RevId: 26247e21d9
|
3 years ago |
Megvii Engine Team
|
c55fda9a7c
|
fix(fastrun): don't kill profiling worker
GitOrigin-RevId: 99a0f11a5a
|
3 years ago |
Megvii Engine Team
|
2775f4580c
|
feat(subgraph): subgraph builder supports jit and custom grad
GitOrigin-RevId: e1a1ebdf1c
|
3 years ago |
Megvii Engine Team
|
3c61e0e02a
|
feat(ops): add JITFusion op
GitOrigin-RevId: 7dc35d4e80
|
3 years ago |
Megvii Engine Team
|
aa587446fc
|
feat(subgraph): support shape inference for CompiledOp
GitOrigin-RevId: a96b8f3446
|
3 years ago |
Megvii Engine Team
|
1c1e9b002d
|
fix(rng): init layout strides
GitOrigin-RevId: 9833d866da
|
3 years ago |
Megvii Engine Team
|
9527859cc8
|
feat(opcache): add ndim and has_value to cache key
GitOrigin-RevId: ad073d389e
|
3 years ago |
Megvii Engine Team
|
cbb47089a6
|
perf(interpreter): add fastpath for GetVarShape
GitOrigin-RevId: d1ac4e7fe3
|
3 years ago |
Megvii Engine Team
|
b458178847
|
feat(opr): add mutable tensor opr
GitOrigin-RevId: 7f8a3d7b66
|
3 years ago |
Megvii Engine Team
|
47fe766310
|
feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr
GitOrigin-RevId: 932e7689e8
|
3 years ago |
Megvii Engine Team
|
dcc9693582
|
feat(dnn/cuda): add heuristic rule for implicit batched gemm large kernel dwconv2d kernels
GitOrigin-RevId: 2d2c213bfd
|
3 years ago |
Megvii Engine Team
|
6cefabe734
|
fix(dnn/cuda): fix ci
GitOrigin-RevId: 8267e5f9dd
|
3 years ago |
Megvii Engine Team
|
888f4e46ae
|
feat(dnn/cuda): add implicit bmm large kernel dwconv2d dgrad kernels
GitOrigin-RevId: fcb7974d62
|
3 years ago |
Megvii Engine Team
|
08d8635ff5
|
feat(dnn/cuda): add implicit bmm large kernel dwconv2d fprop impl
GitOrigin-RevId: feb09ebb58
|
3 years ago |
Megvii Engine Team
|
93ceb80ad2
|
refactor(imperative): fix broadcast,reshape,reduce
GitOrigin-RevId: ee3dc1487d
|
3 years ago |
Megvii Engine Team
|
d919aaebc7
|
test(imperative): reopen special interpolate test and sync when test rng
GitOrigin-RevId: e3d03b4d1d
|
3 years ago |
Megvii Engine Team
|
ca2deebc0f
|
fix(imperative/tensor): make @ operator has the same functionality as matmul functional
GitOrigin-RevId: bf6136cc1a
|
3 years ago |
Megvii Engine Team
|
e860a08386
|
refactor(mge/indexing): move indexing into c++
GitOrigin-RevId: 43fbdb22dd
|
3 years ago |
Megvii Engine Team
|
e6706be23a
|
refactor(imperative): remove infer_output_mem_desc
GitOrigin-RevId: bff62b33a0
|
3 years ago |
Megvii Engine Team
|
a5af35c18c
|
refactor(imperative): remove command buffer
GitOrigin-RevId: 83c8cb6d3b
|
3 years ago |
Megvii Engine Team
|
bdb853ee6f
|
fix(mgb): fix extra device malloc when load MultipleDeviceTensorWithFormatHolder
GitOrigin-RevId: adf4a7f77a
|
3 years ago |
Megvii Engine Team
|
406115dba0
|
fix(imperative): syncbn fp16 support
GitOrigin-RevId: 6059d5b76b
|
3 years ago |
Megvii Engine Team
|
d5ef792309
|
perf(lite): optimized lite tensor get data by share
GitOrigin-RevId: 62e48ca539
|
3 years ago |
huangxinda
|
ce9ad07a27
|
feat(ci): update ci and readme
|
3 years ago |
Megvii Engine Team
|
884865703d
|
test(trace): test subtensor on unknown shape
GitOrigin-RevId: 1b5cfa4e0a
|
3 years ago |
Megvii Engine Team
|
c34a75d0f4
|
fix(trace): assume result is not scalar when shape is valid
GitOrigin-RevId: beee2d0f28
|
3 years ago |
Megvii Engine Team
|
bebb2cf4c3
|
Merge pull request #428 from P2Oileen:fix-pad
GitOrigin-RevId: f33ea46ad6
|
3 years ago |
Megvii Engine Team
|
e2b79ea00e
|
feat(mgb): reduce the number of trtruntimeopr create contexts
GitOrigin-RevId: 14e5d1769e
|
3 years ago |
Megvii Engine Team
|
6157d9cfef
|
fix(traced_module): fix Module compatible issue and traced module getattr check
GitOrigin-RevId: 62eb3bfb10
|
3 years ago |
Megvii Engine Team
|
26b52a61de
|
feat(lite): add get model infomation before create network interface
GitOrigin-RevId: e499f3ebf8
|
3 years ago |
Megvii Engine Team
|
5e17b3e4c6
|
Merge pull request #426 from Qsingle:fix-pixel_suffle
GitOrigin-RevId: db9a0f7551
|
3 years ago |
Megvii Engine Team
|
2bebe80e93
|
fix(imperative): fix the default pickle protocol version of save
GitOrigin-RevId: fab2dc7369
|
3 years ago |
Xinran Xu
|
f02cd2d28b
|
Merge pull request #436 from bealwang/master
docs(readme): add more badges
|
3 years ago |
王彪
|
df4153dc71
|
docs(readme): add more badges
|
3 years ago |
XindaH
|
ea91babbce
|
Merge pull request #435 from MegEngine/try-import
|
3 years ago |
Megvii Engine Team
|
8e94af9d78
|
Merge pull request #400 from jieli-matrix:docstring-svd
GitOrigin-RevId: 3bcbea3440
|
3 years ago |
Megvii Engine Team
|
260923e11c
|
perf(aarch64): optimize aarch64 uint16 relayout with block_w==3
GitOrigin-RevId: fe6aaaac0c
|
3 years ago |