* Added init tensor calling code

* Added get_alloc_size forwarding

* Cleaned up and improved type/error handling.

* fix: remove trailing whitespaces.

* Cleanup and use GGML error logging functions.

* Handle potentially dangerous edge cases.

* Apply suggestions from code review

Co-authored-by: Diego Devesa <[email protected]>

---------

Co-authored-by: Diego Devesa <[email protected]>

…tary driver (llama/11074)

* Vulkan: Add device-specific blacklist for coopmat for the AMD proprietary driver

* Add (TM) to AMD name check

* CUDA: add BF16 support

…ama/11087)

* SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6

* Revert "SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6"

This reverts commit f62dc45f318e48d375e7734b34cbddee81deed52.

* Reland: Use get_multi_ptr instead of deprecated get_pointer in wkv6

Remove duplicated macros, use GGML_LOG_ERROR for errors

* GGUF: C++ refactor, backend support, misc fixes

remove ggml_tensor.backend

update CODEOWNERS [no ci]

remove gguf_get_data from API

revise GGUF API data types

* fix: Vulkan shader gen binary path when cross compiling

…(llama/11117)

* Disable GL_KHR_cooperative_matrix Vulkan extension if not available.

* Perform Vulkan extensions checks in a more sensible order

* Remove unnecessary #ifdef directive

This change upstreams llamafile's cpu matrix
multiplication kernels for ppc64le using MMA
builtins for quantised int8 datatype.

This change results in 10% - 70% improvement
in total speed(ie all tokens/total time), across
various batch sizes.

The patch is tested with Meta-Lllama-3-8B,
Mistral-7B, Llama-2-7B-chat-hf models on a
IBM POWER10 machine.

Signed-off-by: Amrita H S <[email protected]>

Signed-off-by: hydai <[email protected]>

* SYCL: refactor ggml_sycl_compute_forward

* SYCL: add back GGML_USED(dst) to ggml_sycl_cpy

* SYCL: add function name to noop debug

* SYCL: Some device info print refactoring and add details of XMX availability

llama: add support for QRWKV6 model architecture (llama/11001)

* WIP: Add support for RWKV6Qwen2

Signed-off-by: Molly Sophia <[email protected]>

* RWKV: Some graph simplification

Signed-off-by: Molly Sophia <[email protected]>

* Add support for RWKV6Qwen2 with cpu and cuda GLA

Signed-off-by: Molly Sophia <[email protected]>

* RWKV6[QWEN2]: Concat lerp weights together to reduce cpu overhead

Signed-off-by: Molly Sophia <[email protected]>

* Fix some typos

Signed-off-by: Molly Sophia <[email protected]>

* code format changes

Signed-off-by: Molly Sophia <[email protected]>

* Fix wkv test & add gla test

Signed-off-by: Molly Sophia <[email protected]>

* Fix cuda warning

Signed-off-by: Molly Sophia <[email protected]>

* Update README.md

Signed-off-by: Molly Sophia <[email protected]>

* Update ggml/src/ggml-cuda/gla.cu

Co-authored-by: Georgi Gerganov <[email protected]>

* Fix fused lerp weights loading with RWKV6

Signed-off-by: Molly Sophia <[email protected]>

* better sanity check skipping for QRWKV6 in llama-quant

thanks @compilade

Signed-off-by: Molly Sophia <[email protected]>
Co-authored-by: compilade <[email protected]>

---------

Signed-off-by: Molly Sophia <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: compilade <[email protected]>

…roup_size_control validation error (llama/11161)

* Vulkan: Remove float16 use in shaders

* Fix validation error about subgroup_size_control extension

… (llama/11211)

Build fails when using HIP and GGML_BACKEND_DL:
```
/usr/bin/ld: ../ggml/src/libggml.so: undefined reference to `ggml_backend_cuda_reg'
collect2: error: ld returned 1 exit status
```
This patch fixes this.

…e improvements) (llama/11042)

* Refactor: Moves cuda graph executable update step to separate function.

* Refactor: Moves cuda graph update check to separate function.

* Refactor: Moves cuda graph maintenance (update or adjusting copy parameters) to separate function for improved readability.

* Fix: Adds missing reference to maintain_cuda_graph() definition.

* Refactor: Improves structure and abstractions by moving CUDA graph evaluation and capture to its own function.

* Refactor: Moves node graph checks and copy ops into individual function for improved readability.

* Refactor: Removes code permanently excluded from compilation to increase readability.

* Style: Adds missing newline

* Style: Consolidates several neighboring '#ifdef USE_CUDA_GRAPH' into a single one

* Refactor: Makes 'cuda_graph_update_required' a local variable

* remove double lines between functions

---------

Co-authored-by: slaren <[email protected]>

ggml-ci

---------

Co-authored-by: Skyler Szot <[email protected]>
Co-authored-by: Shangqing Gu <[email protected]>
Co-authored-by: Alexander Angus <[email protected]>
Co-authored-by: Hongqiang Wang <[email protected]>
Co-authored-by: Max Krasnyansky <[email protected]>

ggml-ci