Validate the memory requested for the infer request is not out of bounds #7083
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
Tabrizian
reviewed
Apr 9, 2024
kthui
reviewed
Apr 9, 2024
jbkyang-nvi
changed the title
Tabrizian
reviewed
Apr 10, 2024
Tabrizian
reviewed
Apr 10, 2024
…rence-server/server into kyang-validate-shm-byte-size
rmccorm4
reviewed
Apr 11, 2024
| @@ -295,7 +317,7 @@ def test_too_big_shm(self): | |||
| def test_mixed_raw_shm(self): | |||
| # Mix of shared memory and RAW inputs | |||
| error_msg = [] | |||
| shm_handles = self._configure_sever() | |||
| shm_handles = self._configure_sever(shm_byte_size=256) | |||
There was a problem hiding this comment.
My PR will have some conflicts with this PR, but you should be able to use the create_byte_size and register_byte_size args in the same way. Let me know if you're good with it: #7093
There was a problem hiding this comment.
Francesco's PR will also likely have some merge conflicts: #7048
Tabrizian
previously approved these changes
Apr 11, 2024
kthui
previously approved these changes
Apr 11, 2024
Tabrizian
approved these changes
Apr 12, 2024
jbkyang-nvi
added a commit
to triton-inference-server/client
that referenced
this pull request
Apr 12, 2024
rmccorm4
reviewed
Apr 12, 2024
| @@ -292,7 +328,7 @@ def test_too_big_shm(self): | |||
| def test_mixed_raw_shm(self): | |||
| # Mix of shared memory and RAW inputs | |||
| error_msg = [] | |||
| shm_handles = self._configure_sever(shm_byte_size=256) | |||
| shm_handles = self._configure_server() | |||
There was a problem hiding this comment.
Was this supposed to have a value of 256 passed to it? or doesn't matter for this test case?
There was a problem hiding this comment.
I think it was only needed because I had a bug so I removed it..
jbkyang-nvi
added a commit
that referenced
this pull request
Apr 12, 2024
…nds (#7083) Validate that memory offset and byte size requested is not out of bounds of registered memory. Previously in #6914 we checked out of bounds offset for shared memory requests. This PR also adds more testing to verify the block of memory is in fact in bounds. Client change: triton-inference-server/client#565
jbkyang-nvi
added a commit
to triton-inference-server/client
that referenced
this pull request
Apr 12, 2024
This was referenced Apr 12, 2024
Merged
mc-nv
pushed a commit
to triton-inference-server/client
that referenced
this pull request
Apr 12, 2024
mc-nv
pushed a commit
that referenced
this pull request
Apr 12, 2024
…nds (#7083) (#7111) Validate that memory offset and byte size requested is not out of bounds of registered memory. Previously in #6914 we checked out of bounds offset for shared memory requests. This PR also adds more testing to verify the block of memory is in fact in bounds. Client change: triton-inference-server/client#565
This was referenced Apr 18, 2024
jbkyang-nvi
added a commit
that referenced
this pull request
Apr 19, 2024
Fixes windows build issues caused by: #7083
fpetrini15
pushed a commit
to triton-inference-server/perf_analyzer
that referenced
this pull request
Jun 26, 2024
fpetrini15
pushed a commit
to triton-inference-server/perf_analyzer
that referenced
this pull request
Jul 29, 2024
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.
Previously in #6914 we checked out of bounds
offsetfor shared memory requests. This PR updates to a more comprehensive test of verifying that the block of memory is in fact in bounds.Client change: triton-inference-server/client#565