ORT 1.25.1 release: version bump and cherry-pick #27907 (#28149)

Version bump to 1.25.1.

This cherry-picks the following commits for the release:

| Commit ID | PR Number | Commit Title |
|-----------|-----------|-------------|
| e532c21 | #27842 | linear attention signature |
| 410f5a8 | #27752 | +rotemb, +rmsnorm, reshape->opset-25,
transpose->opset-24 |
| 0fedb26 | #27907 | Add LinearAttention and CausalConvState ops for
Qwen3.5 |
| 3ac6040 | #27996 | webgpu support for qwen3.5 |
| c36c422 | #27998 | [WebGPU EP] Fuse QMoE 1-token decode path to
reduce GPU dispatches |
| 94f32ec | #27289 | [CORE]: Improve filesystem error messages during
Linux device discovery |
| dce77a3 | #28118 | Fix lack of auth on python packaging |

---------

Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: eserscor <erscor@microsoft.com>
Co-authored-by: Sanaa Hamel <sanaahamel@microsoft.com>
Co-authored-by: Guenther Schmuelling <guschmue@microsoft.com>
Co-authored-by: Stephan Seitz <sseitz@nvidia.com>
Co-authored-by: Jiajia Qin <jiajiaqin@microsoft.com>

Author: 8 people

VERSION_NUMBER

@@ -1 +1 @@
-1.25.0
+1.25.1

docs/ContribOperators.md

@@ -15,6 +15,7 @@ Do not modify directly.*
   * <a href="#com.microsoft.BitmaskBiasDropout">com.microsoft.BitmaskBiasDropout</a>
   * <a href="#com.microsoft.BitmaskDropout">com.microsoft.BitmaskDropout</a>
   * <a href="#com.microsoft.CDist">com.microsoft.CDist</a>
+  * <a href="#com.microsoft.CausalConvWithState">com.microsoft.CausalConvWithState</a>
   * <a href="#com.microsoft.ComplexMul">com.microsoft.ComplexMul</a>
   * <a href="#com.microsoft.ComplexMulConj">com.microsoft.ComplexMulConj</a>
   * <a href="#com.microsoft.ConvTransposeWithDynamicPads">com.microsoft.ConvTransposeWithDynamicPads</a>
@@ -49,6 +50,7 @@ Do not modify directly.*
   * <a href="#com.microsoft.GroupQueryAttention">com.microsoft.GroupQueryAttention</a>
   * <a href="#com.microsoft.Inverse">com.microsoft.Inverse</a>
   * <a href="#com.microsoft.Irfft">com.microsoft.Irfft</a>
+  * <a href="#com.microsoft.LinearAttention">com.microsoft.LinearAttention</a>
   * <a href="#com.microsoft.LongformerAttention">com.microsoft.LongformerAttention</a>
   * <a href="#com.microsoft.MatMulBnb4">com.microsoft.MatMulBnb4</a>
   * <a href="#com.microsoft.MatMulFpQ4">com.microsoft.MatMulFpQ4</a>
@@ -900,6 +902,68 @@ This version of the operator has been available since version 1 of the 'com.micr
 </dl>
 
 
+### <a name="com.microsoft.CausalConvWithState"></a><a name="com.microsoft.causalconvwithstate">**com.microsoft.CausalConvWithState**</a>
+
+  Stateful causal depthwise convolution, generalized to N spatial dimensions.
+  
+  Used by Gated DeltaNet (Qwen3.5) and Mamba (Jamba, FalconMamba) as a preprocessing step.
+  Replaces the 3-op pattern (Concat + Conv + Slice) with a single fused operation.
+  
+  The convolution is causal (looks only at current and past positions along the last
+  spatial dimension) and depthwise (each channel is convolved independently with its own kernel).
+  
+  Input layout is channels-first: (batch_size, channels, ...).
+  Weight layout: (channels, 1, k_1, ...) for depthwise convolution.
+  The carry state stores the last (k-1) positions along the causal axis for incremental decode.
+  
+  The ndim attribute generalizes the op to 1D, 2D, or 3D spatial dimensions. Causality is
+  enforced on the last spatial dimension only.
+  
+  The optional activation attribute supports fused SiLU/Swish activation.
+
+#### Version
+
+This version of the operator has been available since version 1 of the 'com.microsoft' operator set.
+
+#### Attributes
+
+<dl>
+<dt><tt>activation</tt> : string</dt>
+<dd>Fused activation function. One of: 'silu', 'swish', 'none'. Default is 'none'.</dd>
+<dt><tt>ndim</tt> : int</dt>
+<dd>Spatial dimensionality: 1, 2, or 3. Default is 1.</dd>
+</dl>
+
+#### Inputs (2 - 4)
+
+<dl>
+<dt><tt>input</tt> : T</dt>
+<dd>Input tensor with shape (batch_size, channels, ...). Channels-first layout. Spatial dims: 1D: (L,); 2D: (H, W); 3D: (D, H, W).</dd>
+<dt><tt>weight</tt> : T</dt>
+<dd>Depthwise convolution kernel with shape (channels, 1, k_1, ...). Spatial kernel sizes: (k_1, ..., k_ndim).</dd>
+<dt><tt>bias</tt> (optional) : T</dt>
+<dd>Optional per-channel bias with shape (channels).</dd>
+<dt><tt>past_state</tt> (optional) : T</dt>
+<dd>Carry state from previous step. For ndim=1: (batch_size, channels, k_1 - 1). If not provided, padding is zero.</dd>
+</dl>
+
+#### Outputs
+
+<dl>
+<dt><tt>output</tt> : T</dt>
+<dd>Convolution output with same shape as input.</dd>
+<dt><tt>present_state</tt> : T</dt>
+<dd>Updated carry state. For ndim=1: (batch_size, channels, k_1 - 1). Contains the last (k-1) values from the virtual input along the causal axis.</dd>
+</dl>
+
+#### Type Constraints
+
+<dl>
+<dt><tt>T</tt> : tensor(float), tensor(float16), tensor(bfloat16)</dt>
+<dd>Constrain input and output types to float tensors.</dd>
+</dl>
+
+
 ### <a name="com.microsoft.ComplexMul"></a><a name="com.microsoft.complexmul">**com.microsoft.ComplexMul**</a>
 
 #### Version
@@ -2703,6 +2767,79 @@ This version of the operator has been available since version 1 of the 'com.micr
 </dl>
 
 
+### <a name="com.microsoft.LinearAttention"></a><a name="com.microsoft.linearattention">**com.microsoft.LinearAttention**</a>
+
+  Unified linear attention operator for autoregressive decoding (T=1) and prefill (T>1).
+  
+  All inputs use 3D packed format [B, T, H*D]; q_num_heads and kv_num_heads are always
+  required. The op internally unpacks to 4D for computation.
+  
+  The update_rule attribute selects the recurrence type:
+  - "linear": S_t = S_{t-1} + k_t ⊗ v_t; o_t = scale * q_t^T S_t
+  - "gated": S_t = exp(g_t) * S_{t-1} + k_t ⊗ v_t; o_t = scale * q_t^T S_t
+  - "delta": S_t = S_{t-1} + β_t * k_t ⊗ (v_t - S_{t-1}^T k_t); o_t = scale * q_t^T S_t
+  - "gated_delta": S_t = exp(g_t) * S_{t-1} + β_t * k_t ⊗ (v_t - exp(g_t) * S_{t-1}^T k_t); o_t = scale * q_t^T S_t
+  
+  where g_t is the decay (in log-space), β_t is the update rate, and ⊗ denotes outer product.
+  
+  Semantics: Equivalent to running the recurrent update sequentially for each token,
+  but may be implemented using chunk-parallel algorithms for GPU efficiency.
+
+#### Version
+
+This version of the operator has been available since version 1 of the 'com.microsoft' operator set.
+
+#### Attributes
+
+<dl>
+<dt><tt>chunk_size</tt> : int</dt>
+<dd>Chunk size for the chunk-parallel WY decomposition during prefill (T>1). Tuning hint; does not affect output correctness.</dd>
+<dt><tt>kv_num_heads</tt> : int (required)</dt>
+<dd>Number of key/value heads. Always required.</dd>
+<dt><tt>q_num_heads</tt> : int (required)</dt>
+<dd>Number of query heads. Always required.</dd>
+<dt><tt>scale</tt> : float</dt>
+<dd>Output scaling factor. When 0.0 (default), derives d_k = query.shape[-1] / q_num_heads and uses 1/sqrt(d_k). Set explicitly to override.</dd>
+<dt><tt>update_rule</tt> : string</dt>
+<dd>The update rule for the linear attention recurrence. One of: 'linear', 'gated', 'delta', 'gated_delta'. Default is 'gated_delta'.</dd>
+</dl>
+
+#### Inputs (3 - 6)
+
+<dl>
+<dt><tt>query</tt> : T</dt>
+<dd>Query vectors with 3D packed shape (B, T, H_q * d_k). Heads are packed into the last dimension.</dd>
+<dt><tt>key</tt> : T</dt>
+<dd>Key vectors with 3D packed shape (B, T, H_kv * d_k). Should be L2-normalized for delta/gated_delta modes.</dd>
+<dt><tt>value</tt> : T</dt>
+<dd>Value vectors with 3D packed shape (B, T, H_kv * d_v).</dd>
+<dt><tt>past_state</tt> (optional) : S</dt>
+<dd>Recurrent state from previous step with shape (B, H_kv, d_k, d_v). Always 4D. If not provided, defaults to zeros.</dd>
+<dt><tt>decay</tt> (optional) : T</dt>
+<dd>Exponential decay gate in log-space. 3D packed shape: (B, T, H_kv * d_k) for per-key-dimension decay (GLA/RWKV-6), or (B, T, H_kv) for per-head scalar decay (DeltaNet/RetNet). Required for 'gated' and 'gated_delta' modes.</dd>
+<dt><tt>beta</tt> (optional) : T</dt>
+<dd>Update rate (sigmoid output). 3D packed shape: (B, T, H_kv) or (B, T, 1). Required for 'delta' and 'gated_delta' modes.</dd>
+</dl>
+
+#### Outputs
+
+<dl>
+<dt><tt>output</tt> : T</dt>
+<dd>Attention output with 3D packed shape (B, T, H_q * d_v).</dd>
+<dt><tt>present_state</tt> : S</dt>
+<dd>Updated recurrent state with shape (B, H_kv, d_k, d_v). Always 4D.</dd>
+</dl>
+
+#### Type Constraints
+
+<dl>
+<dt><tt>T</tt> : tensor(float), tensor(float16), tensor(bfloat16)</dt>
+<dd>Constrain input and output types to float tensors.</dd>
+<dt><tt>S</tt> : tensor(float), tensor(float16), tensor(bfloat16)</dt>
+<dd>Constrain state types to float tensors.</dd>
+</dl>
+
+
 ### <a name="com.microsoft.LongformerAttention"></a><a name="com.microsoft.longformerattention">**com.microsoft.LongformerAttention**</a>
 
   Longformer Self Attention with a local context and a global context. Tokens attend locally: Each token

docs/OperatorKernels.md

@@ -564,6 +564,7 @@ Do not modify directly.*
 |BiasGelu|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|1+|**T** = tensor(float)|
 |BifurcationDetector|*in* src_tokens:**T**<br> *in* cur_tokens:**T**<br> *in* prev_suffix_match_idx:**T**<br> *in* pred_tokens:**T**<br> *out* tokens:**T**<br> *out* suffix_match_idx:**T**|1+|**T** = tensor(int64)|
 |CDist|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|1+|**T** = tensor(double), tensor(float)|
+|CausalConvWithState|*in* input:**T**<br> *in* weight:**T**<br> *in* bias:**T**<br> *in* past_state:**T**<br> *out* output:**T**<br> *out* present_state:**T**|1+|**T** = tensor(float)|
 |ConvTransposeWithDynamicPads|*in* X:**T**<br> *in* W:**T**<br> *in* Pads:**tensor(int64)**<br> *in* B:**T**<br> *out* Y:**T**|1+|**T** = tensor(float)|
 |CropAndResize|*in* X:**T1**<br> *in* rois:**T1**<br> *in* batch_indices:**T2**<br> *in* crop_size:**T2**<br> *out* Y:**T1**|1+|**T1** = tensor(float)<br/> **T2** = tensor(int32)|
 |DecoderMaskedMultiHeadAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* mask_index:**M**<br> *in* attention_bias:**T**<br> *in* past_key:**T**<br> *in* past_value:**T**<br> *in* past_sequence_length:**M**<br> *in* beam_width:**M**<br> *in* cache_indirection:**M**<br> *in* bias:**T**<br> *out* output:**T**<br> *out* present_key:**T**<br> *out* present_value:**T**<br> *out* qk:**QK**|1+|**T** = tensor(float)|
@@ -584,6 +585,7 @@ Do not modify directly.*
 |GridSample|*in* X:**T1**<br> *in* Grid:**T1**<br> *out* Y:**T2**|1+|**T1** = tensor(float)<br/> **T2** = tensor(float)|
 |GroupQueryAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* past_key:**T_CACHE**<br> *in* past_value:**T_CACHE**<br> *in* seqlens_k:**M**<br> *in* total_sequence_length:**M**<br> *in* cos_cache:**T**<br> *in* sin_cache:**T**<br> *in* position_ids:**tensor(int64)**<br> *in* attention_bias:**T**<br> *in* head_sink:**T**<br> *in* k_scale:**T_KV_SCALE**<br> *in* v_scale:**T_KV_SCALE**<br> *out* output:**T**<br> *out* present_key:**T_CACHE**<br> *out* present_value:**T_CACHE**<br> *out* output_qk:**T**|1+|**M** = tensor(int32)<br/> **T** = tensor(float), tensor(float16)|
 |Inverse|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(double), tensor(float), tensor(float16)|
+|LinearAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* past_state:**S**<br> *in* decay:**T**<br> *in* beta:**T**<br> *out* output:**T**<br> *out* present_state:**S**|1+|**T** = tensor(float)|
 |MatMulBnb4|*in* A:**T1**<br> *in* B:**T2**<br> *in* absmax:**T1**<br> *out* Y:**T1**|1+|**T1** = tensor(float)<br/> **T2** = tensor(uint8)|
 |MatMulFpQ4|*in* A:**T1**<br> *in* B:**T2**<br> *in* B_shape:**T3**<br> *out* Y:**T1**|1+|**T1** = tensor(float)<br/> **T2** = tensor(uint8)<br/> **T3** = tensor(int64)|
 |MatMulInteger16|*in* A:**T1**<br> *in* B:**T2**<br> *out* Y:**T3**|1+|**T1** = tensor(int16)<br/> **T2** = tensor(int16)<br/> **T3** = tensor(int32)|
@@ -1031,6 +1033,7 @@ Do not modify directly.*
 |BiasSplitGelu|*in* X:**T**<br> *in* bias:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
 |BitmaskBiasDropout|*in* data:**T**<br> *in* bias:**T**<br> *in* residual:**T**<br> *in* ratio:**T1**<br> *in* training_mode:**T2**<br> *out* output:**T**<br> *out* mask:**T3**|1+|**T** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)<br/> **T1** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)<br/> **T2** = tensor(bool)<br/> **T3** = tensor(uint32)|
 |BitmaskDropout|*in* data:**T**<br> *in* ratio:**T1**<br> *in* training_mode:**T2**<br> *out* output:**T**<br> *out* mask:**T3**|1+|**T** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)<br/> **T1** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)<br/> **T2** = tensor(bool)<br/> **T3** = tensor(uint32)|
+|CausalConvWithState|*in* input:**T**<br> *in* weight:**T**<br> *in* bias:**T**<br> *in* past_state:**T**<br> *out* output:**T**<br> *out* present_state:**T**|1+|**T** = tensor(float), tensor(float16)|
 |ComplexMul|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|1+|**T** = tensor(float), tensor(float16)|
 |ComplexMulConj|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|1+|**T** = tensor(float), tensor(float16)|
 |ConvTransposeWithDynamicPads|*in* X:**T**<br> *in* W:**T**<br> *in* Pads:**tensor(int64)**<br> *in* B:**T**<br> *out* Y:**T**|1+|**T** = tensor(float)|
@@ -1055,6 +1058,7 @@ Do not modify directly.*
 |GroupQueryAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* past_key:**T_CACHE**<br> *in* past_value:**T_CACHE**<br> *in* seqlens_k:**M**<br> *in* total_sequence_length:**M**<br> *in* cos_cache:**T**<br> *in* sin_cache:**T**<br> *in* position_ids:**tensor(int64)**<br> *in* attention_bias:**T**<br> *in* head_sink:**T**<br> *in* k_scale:**T_KV_SCALE**<br> *in* v_scale:**T_KV_SCALE**<br> *out* output:**T**<br> *out* present_key:**T_CACHE**<br> *out* present_value:**T_CACHE**<br> *out* output_qk:**T**|1+|**M** = tensor(int32)<br/> **T** = tensor(bfloat16), tensor(float16)<br/> **T_CACHE** = tensor(bfloat16), tensor(float16), tensor(float8e4m3fn), tensor(int8)<br/> **T_KV_SCALE** = tensor(float)|
 |Inverse|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(double), tensor(float), tensor(float16)|
 |Irfft|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(double), tensor(float), tensor(float16)|
+|LinearAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* past_state:**S**<br> *in* decay:**T**<br> *in* beta:**T**<br> *out* output:**T**<br> *out* present_state:**S**|1+|**T** = tensor(float), tensor(float16)|
 |LongformerAttention|*in* input:**T**<br> *in* weight:**T**<br> *in* bias:**T**<br> *in* mask:**T**<br> *in* global_weight:**T**<br> *in* global_bias:**T**<br> *in* global:**G**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
 |MatMulBnb4|*in* A:**T1**<br> *in* B:**T2**<br> *in* absmax:**T1**<br> *out* Y:**T1**|1+|**T1** = tensor(bfloat16), tensor(float), tensor(float16)<br/> **T2** = tensor(uint8)|
 |MatMulNBits|*in* A:**T1**<br> *in* B:**T2**<br> *in* scales:**T1**<br> *in* zero_points:**T3**<br> *in* g_idx:**T4**<br> *in* bias:**T1**<br> *out* Y:**T1**|1+|**T1** = tensor(bfloat16), tensor(float), tensor(float16)<br/> **T2** = tensor(uint8)<br/> **T3** = tensor(bfloat16), tensor(float), tensor(float16), tensor(uint8)|

docs/python/README.rst

@@ -8,6 +8,11 @@ For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://ak
 Changes
 -------
 
+1.25.1
+^^^^^^
+
+Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.25.1
+
 1.25.0
 ^^^^^^
 

js/common/lib/version.ts

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.25.0';
+export const version = '1.25.1';

js/common/package-lock.json

@@ -2,7 +2,7 @@
   "license": "MIT",
   "type": "module",
   "name": "onnxruntime-common",
-  "version": "1.25.0",
+  "version": "1.25.1",
   "repository": {
     "url": "https://github.com/Microsoft/onnxruntime.git",
     "type": "git"

js/common/package.json

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.25.0';
+export const version = '1.25.1';

js/node/lib/version.ts

@@ -11,7 +11,7 @@
       6
     ]
   },
-  "version": "1.25.0",
+  "version": "1.25.1",
   "dependencies": {
     "adm-zip": "^0.5.16",
     "global-agent": "^4.1.3",