[auto] Sync version 2406031220.0.0+llamacpp-release.b3075

== Relevant log messages from source repo:

commit 3d7ebf63123b8652fb7bbecef7ba731202309901
Author: 0cc4m <picard12@live.de>
Date:   Mon Jun 3 10:59:14 2024 +0200

    Vulkan Mixture of Experts (MoE) support (#7628)

    * Finish Vulkan mul_mat_id implementation

    * Add Vulkan sum_rows and div ops

    * Fix MUL_MAT_ID matrix matrix shader

    * Fix MUL_MAT_ID matrix vector shader dispatch size

    * Fix MUL_MAT_ID matrix vector shader and dispatch code

    * Update Vulkan CPU offload for MUL_MAT_ID

    * Fix crash when using split mode none and setting a main GPU

commit a10cda58d3199cd85305e0f03a8c6056714ae2e8
Author: Andy Tai <andy-tai@users.noreply.github.com>
Date:   Mon Jun 3 01:06:24 2024 -0700

    cmake : add pkg-config spec file for llama.cpp (#7702)

commit 6f28a333c1e3fdfdc7b4f9d0367f2b41a9b7e9d4
Author: zhangkaihuo <zhangkaihuo@gmail.com>
Date:   Mon Jun 3 15:49:30 2024 +0800

    llama : MiniCPM support tied embeddings (#7664)

    * support lm_head

    * remove the code block

    ---------

    Co-authored-by: zhangkaihuo <zhangkaihuo@modelbest.cn>

commit 549279d8049d78620a2b081e26edb654f83c3bbd
Author: Georgi Gerganov <ggerganov@gmail.com>
Date:   Mon Jun 3 08:34:43 2024 +0300

    llama : avoid double token-to-piece cache (#7654)

    ggml-ci

commit 9e405b6e2ecb888e860f7b92720b4809e21b3915
Author: woachk <24752637+woachk@users.noreply.github.com>
Date:   Mon Jun 3 07:32:16 2024 +0200

    kompute : implement op_getrows_f32 (#6403)

    op_getrows_f32 is required since ggerganov/llama.cpp#6122
    for the Vulkan w/ Kompute backend to be functional.

    As such, implement this op to make this backend functional again.

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ggml-sys-bleedingedge"
-version = "2406030051.0.0+llamacpp-release.b3070"
+version = "2406031220.0.0+llamacpp-release.b3075"
 description = "Bleeding edge low-level bindings to GGML. "
 repository = "https://github.com/KerfuffleV2/ggml-sys-bleedingedge"
 keywords = ["deep-learning", "machine-learning", "tensors", "ggml", "ml"]

VERSION.txt

@@ -1 +1 @@
-2406030051.0.0+llamacpp-release.b3070
+2406031220.0.0+llamacpp-release.b3075

ggml-tag-current.txt

@@ -1 +1 @@
-b3070
+b3075

ggml-tag-previous.txt

@@ -1 +1 @@
-b3063
+b3070