[xpu]: add matmul int8_t #9764
Merged
[xpu]: add matmul int8_t #9764
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gitliuyf
requested review from
zhupengyang,
hong19860320 and
liyancas
as code owners
|
Thanks for your contribution! |
gitliuyf
force-pushed
the
matmul_int64
branch
6 times, most recently
from
aea77e4
to
30de989
Compare
newway
reviewed
Nov 29, 2022
lite/kernels/xpu/matmul_compute.cc
Outdated
| } | ||
| const float* xw_maxptr = | ||
| param.enable_int8 ? reinterpret_cast<float*>(input_max_guard_->addr_) |
There was a problem hiding this comment.
x_maxptr跟w_maxptr分2个变量, 值在满足量化和x/y输入相同时才相同
newway
reviewed
Nov 29, 2022
lite/kernels/xpu/matmul_compute.cc
Outdated
| mat_dim_a.width_, // k | ||
| mat_dim_a.trans_, // x_trans | ||
| mat_dim_b.trans_, // w_trans | ||
| xw_maxptr, // x_maxptr |
gitliuyf
force-pushed
the
matmul_int64
branch
from
30de989
to
53db1c4
Compare
xiuxin121
reviewed
Dec 1, 2022
| @@ -237,6 +237,15 @@ using XPUFC_Int8_FP32_FP32 = | |||
| using XPUFC_FP32_LOCAL_QUANT = | |||
| xpu::XPUFcCompute<float, float, float, float, PRECISION(kFloat)>; | |||
|
|
|||
| using XPUFC_Int8_Int8_FP32 = | |||
There was a problem hiding this comment.
fc注册了int8和fp32的输入输出，kernel pick之前的逻辑需要林伟改下。否则注册的这些还是使用不了。
|
LGTM |
newway
pushed a commit
to newway/Paddle-Lite
that referenced
this pull request
Mar 6, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.