enable matmul fp16 #27
Open
Conversation
This file contains hidden or 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
also added faster implementation of fp16 MatMul
cjm715
force-pushed
the
chris-enable-matmul-fp16
branch
from
c2c53b7 to
5a40b3e
Compare
ndrego
reviewed
May 13, 2025
Comment on lines
+224
to
+229
| // for (auto& node : graph.Nodes()) { | ||
| // if (IsIsolatedFp16NodeOnCpu(node, graph, cpu_kernel_registry)) { | ||
| // // unassign the node so that NeedInsertCast will return true for it, forcing it to fp32 | ||
| // node.SetExecutionProviderType(""); | ||
| // } | ||
| // } |
There was a problem hiding this comment.
Remove, or block comment using /* ... */ and add a comment as to why we've commented it out.
|
|
||
|
|
||
| // template <> | ||
| // void MatMul<MLFloat16>(ptrdiff_t M, ptrdiff_t N, ptrdiff_t K, const MLFloat16* A, const MLFloat16* B, MLFloat16* C, concurrency::ThreadPool* thread_pool) { |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
this will come in after PR #26