You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "shtinsa (via GitHub)" <gi...@apache.org> on 2024/02/03 10:18:04 UTC
[PR] [Runtime][MemoryPool] [tvm]
shtinsa opened a new pull request, #16517:
URL: https://github.com/apache/tvm/pull/16517
The commit contains new memory manager which limits amount of cached buffers.
The problem appeared on scenario with 4 sequential transformer based networks which generate output with different sizes on each iteration. In this case default PooledAllocator keeps large amount of buffers, for example it was about 2000 unallocated buffers (~1.9GB of memory) at the pool clearance moment. New allocator limits the pool size by 256 entities.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Runtime][MemoryPool] Memory pool with limited cache size [tvm]
Posted by "shtinsa (via GitHub)" <gi...@apache.org>.
shtinsa commented on PR #16517:
URL: https://github.com/apache/tvm/pull/16517#issuecomment-1927557887
> i think some changes that @MasterJH5574 introduced recently would alleviate this situation if we bring outputs that have a maximum upper bound
Frankly speakng this PR supplements 2 cases: the cached buffers large number and the second one is related to CUDA crash after pool de-allocation. The logs show that the deallocation works correctly, the CUDA reports that it has enough of memory to create new buffer, buffer is allocated but inference fails inside of `fused_relax_matmul_relax_add_relax_add_cutlass_(DLTensor*, DLTensor*, DLTensor*, DLTensor*, DLTensor*)` call.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Runtime][MemoryPool] Memory pool with limited cache size [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen closed pull request #16517: [Runtime][MemoryPool] Memory pool with limited cache size
URL: https://github.com/apache/tvm/pull/16517
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Runtime][MemoryPool] Memory pool with limited cache size [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen commented on PR #16517:
URL: https://github.com/apache/tvm/pull/16517#issuecomment-1925421553
i think some changes that @MasterJH5574 introduced recently would alleviate this situation if we bring outputs that have a maximum upper bound
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org