Jesse Cai 157de30f53 [sparse] Update cuSPARSELt to v0.6.2 (#134022) ... Summary: This PR updated cuSPARSELt to v0.6.2. I think we should land https://github.com/pytorch/pytorch/pull/128534 first though. Most of this PR is just enabling tests to run when cuSPARSELt v0.6.2 is available. Unfortunately was running into a bug with fp32 support on Hopper, so I removed fp32 support from the cuSPARSELt backend. I think this should be fine since almost everybody uses the bfloat/float16/int8 kernels. Test Plan: Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: https://github.com/pytorch/pytorch/pull/134022 Approved by: https://github.com/jerryzh168, https://github.com/malfet ghstack dependencies: #128534		2024-08-23 19:34:53 +00:00
..
__init__.py	SparseCsrCUDA: cuDSS backend for linalg.solve (#129856)	2024-08-22 07:57:30 +00:00
_semi_structured_conversions.py	Enable UFMT on all of torch/sparse (#130545)	2024-07-15 22:35:52 +00:00
_semi_structured_ops.py	[BE][Easy][19/19] enforce style for empty lines in import segments in torch/[o-z]*/ (#129771)	2024-08-01 17:07:14 +00:00
_triton_ops_meta.py	Tune _int_bsr_dense_addmm for int8 inputs on A100 (#134035)	2024-08-22 06:43:11 +00:00
_triton_ops.py	Add int8 support to bsr_dense_addmm and bsr_dense_mm Triton kernels (#133855)	2024-08-21 20:44:40 +00:00
semi_structured.py	[sparse] Update cuSPARSELt to v0.6.2 (#134022)	2024-08-23 19:34:53 +00:00