[object Object][object Object]

[object Object]

1. Mapping between CANN and driver versions

[object Object]undefined

2. CANN package mapping

CANN 9.0.1 portfolio contains three packages: Toolkit, operator (ops), and acceleration (NNAL). The following table describes the mapping between the CANN portfolio and subpackages, and these six subpackages allow on-demand installation and independent upgrades:

[object Object][object Object]

[object Object]

For details about how to upgrade a subpackage independently, see .

3. Mapping between CANN ops and Toolkit

The CANN ops package has been decoupled from Toolkit and can be upgraded independently. You can install the CANN ops package on demand.

[object Object]undefined[object Object][object Object]

The following APIs in the transformer library are marked as deprecated in CANN 9.0.0 and will be deleted in versions released after March 30, 2027.

• The aclnnGroupedMatMulAllReduce API is deprecated and replaced with aclnnMatmulAllReduce.
• The aclnnGroupedMatmul, aclnnGroupedMatmulV2, aclnnGroupedMatmulV3, and aclnnGroupedMatmulV4 APIs are deprecated and replaced with aclnnGroupedMatmulV5.
• The aclnnFusedInferAttentionScore/aclnnFusedInferAttentionScoreV2/aclnnFusedInferAttentionScoreV3 API is deprecated and replaced with aclnnFusedInferAttentionScoreV4.
• The aclnnIncreFlashAttention/aclnnIncreFlashAttentionV2/aclnnIncreFlashAttentionV3 API is deprecated and replaced with aclnnIncreFlashAttentionV4.
• The aclnnPromptFlashAttention/aclnnPromptFlashAttentionV2 API is deprecated and replaced with aclnnPromptFlashAttentionV3.
• The aclnnMlaProlog/aclnnMlaPrologV2WeightNz API is deprecated and replaced with aclnnMlaPrologV3WeightNz.
• The aclnnMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnMatmulAllReduce and aclnnAddRmsNorm.
• The aclnnQuantMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnQuantMatmulAllReduceV2 and aclnnAddRmsNorm.
• The aclnnWeightQuantMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnWeightQuantMatmulAllReduce and aclnnAddRmsNorm.
• The aclnnInplaceQuantMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnQuantMatmulAllReduceV2 and aclnnAddRmsNorm.
• The aclnnInplaceMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnMatmulAllReduce and aclnnAddRmsNorm.
• The aclnnInplaceWeightQuantMatmulAllReduceAddRmsNorm API is deprecated and replaced with aclnnWeightQuantMatmulAllReduce and aclnnAddRmsNorm.

[object Object]

The following features of the model compression tool are deprecated. The deprecated features will be deleted in versions later than CANN 9.0.0.

• NUQ
• Mixed precision
• Calibrated approximation
• int4 QAT
• All features of amct_mindspore

[object Object]

• Fixed the issue that the fast recovery process cannot be triggered when a multi-bit error occurred in the on-chip memory of a decode node when the Atlas A2 products run with large-scale EP.
• Fixed the issue that communication timeout occasionally occurred at a random step position after more than 500 steps in a 4K-NPU training job.
• Fixed the issue that refill backlog occurred due to frequent decode restarts in PD disaggregation scenarios.
• Fixed the issue that the custom operator and built-in operator IR prototypes with the same name in the open-source repository did not take effect.
• Fixed the issue that a core dump occasionally occurred during the load test for the aclnnAddmv operator.
• Fixed the issue that an error was reported when starting a 10K-NPU job.
• Fixed the issue that MatMulV3 underperformed than MatMulV2 when involving aclgraph with a specific shape.
• Fixed the precision issue in fused_quant_mat_mul use cases.
• Fixed the precision issue in BatchMatmulV2 use cases with a specific bias.
• Fixed the precision issue of the FAG operator in the GQA and NoMask use cases with short sequences.

[object Object]

For details about the fixed vulnerabilities in open-source and third-party software, see .

[object Object][object Object]

You can now upgrade subpackages on demand.

For example, if you have installed the Ascend-CANN-Toolkit and Ascend-CANN-ops packages of version a.b.c, and the communication library needs to be updated to version x.y.z, you can upgrade the cann-hixl subpackage independently. Replace a.b.c and x.y.z with the actual version numbers.

[object Object]

Before upgrading a subpackage, ensure that the Ascend-CANN-Toolkit and Ascend-CANN-ops packages of the matching version have been installed. If the packages are not installed, install them by referring to .

Subpackage upgrade paths must be the same as that of the main package. The upgrade operations of all subpackages are the same. The following uses [object Object] as an example.

Upgrade scenario 1:

The Ascend-CANN-Toolkit and Ascend-CANN-ops packages are installed in the default path (that is, not using [object Object] for installation).

Upgrade scenario 2:

The Ascend-CANN-Toolkit and Ascend-CANN-ops packages are installed in the specified path [object Object] (that is, specifying [object Object] during installation).