Revert fattn q static shape#155

Closed

cavusmustafa wants to merge 33 commits into

ravi9:masterfrom

cavusmustafa:revert_fattn_q_static_shape

Commits on Apr 22, 2026

Add interface is_model_splitted() to check the c-graph is splited or not

zhaixuejun1993
authored and
wine99
committed
Infer and propagate dynamic-dimension indices for all tensors in the GGML graph in api compute_model_outputs()

zhaixuejun1993
authored and
wine99
committed
Only do this for fallback sub graph

zhaixuejun1993
authored and
wine99
committed
Move dynamic dims compute in graph missmatch

zhaixuejun1993
authored and
wine99
committed
ggml-openvino: fix tensor data handling for PERMUTE/VIEW ops in split models

zhaixuejun1993
authored and
wine99
committed
ggml-openvino:add comments

zhaixuejun1993
authored and
wine99
committed
ggml-openvino: override VIEW op_case to 0 for split model inputs

zhaixuejun1993
authored and
wine99
committed
openvino backend: Handle unsupported VIEW shape-mismatch in OpenVINO backend

zhaixuejun1993
authored and
wine99
committed
Enable additional mul_mat tests and add tensor data saving function (#81)

zhaixuejun1993
authored and
wine99
committed
ggml-openvino: fix CONT/TRANSPOSE mapping and improve dynamic-dimension handling

zhaixuejun1993
authored and
wine99
committed
OpenVINO: add NORM/TANH support and rework SOFT_MAX translation

zhaixuejun1993
authored and
wine99
committed
ggml-openvino: extend VIEW handling

zhaixuejun1993
authored and
wine99
committed
Enable -fa off (#118)
wine99
committed
Enable --context-shift
wine99
committed
Fix llm param compute error for normal softmax not the softmax in attention

zhaixuejun1993
authored and
wine99
committed
OpenVINO backend: fix error for attention size compute in llm param

zhaixuejun1993
authored and
wine99
committed

Commits on Apr 29, 2026

use tensor->extra in infer_request i/o
wine99
committed
OpenVINO backend: refacter the compute_llm_params() func add get_attention_pattern_case to easy extand

zhaixuejun1993
authored and
wine99
committed
OpenVINO backend: clean unused code

zhaixuejun1993
authored and
wine99
committed

Commits on May 4, 2026

Commits on May 6, 2026

1to1 match op update (#146)

cavusmustafa
and
Mustafa Cavus
authored
initial gemma4 support

Mustafa Cavus
authored and
wine99
committed
removed hardcoded names for kv cache slicing

cavusmustafa
authored and
wine99
committed
OpenVINO backend: Add new attention pattern for llm parameters compute

zhaixuejun1993
authored and
wine99
committed
Merge pull request #144 from cavusmustafa/stateless_perf_opt
cavusmustafa
authored