b5190

Force FP32 compute in GLM4 FFN Down (#13101)

* Force FP32 compute in cuBLAS GEMM

* Revert "Force FP32 compute in cuBLAS GEMM"

This reverts commit 6efd872732159ab88ee7b3c1d77ba5ebc83079bd.

* Force F32 compute in GLM4 ffn down

* Edit comment to clarify issue

Co-authored-by: Johannes Gäßler <[email protected]>

---------

Co-authored-by: Johannes Gäßler <[email protected]>

b5189

clip : fix pixtral on some GPU backends (#13097)

* clip : fix pixtral on some GPU backends

* refactor inp_raw set

* rm outdated comment

* fix dynamic size

* add TODO

b5188

change the reorder tensor from init to execute OP (#13003)

b5187

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)

RPC_CMD_SET_TENSOR always returns an empty response and we send this 4
times per token. We can improve TG speed if we don't wait for this empty
response.

The performance impact of this change depends on the network latency.

b5186

clip : remove boi/eoi embeddings for GLM-edge model (#13081)

b5185

embeddings : fix batch sizes (#13076)

ggml-ci

b5184

ggml : fix trailing whitespaces (#0)

b5181

CUDA: use switch statements in constexpr functions (#13095)

b5180

cmake : do not include ./src as public for libllama (#13062)

* cmake : do not include ./src as public for libllama

ggml-ci

* cmake : rework tests

ggml-ci

* llguidance : remove unicode include

ggml-ci

* cmake : make c++17 private

ggml-ci

b5178

arg : add --no-mmproj-offload (#13093)

* arg : add --no-mmproj-offload

* Update common/arg.cpp