gguf-py : add support for endian conversion of BF16 data (ggml-org#16594

)

BF16 requires special handling in this script
while it's a 2-bytes data, but view is 1-byte by default.
Switch to correct view before attempting byteswapping.

With this change correctly byteswapping models like
Meta-Llama-3-8B-Instruct-bf16-GGUF
should be possible.

metal : add opt_step_adamw and op_sum (ggml-org#16529)

* scaffold to support opt step adamw on metal (not written so far)

* add opt-step-adamw kernel for metal

* pass op->src[4] as a separate buffer to the pipeline

* add bounds check to opt-step-adamw kernel

* complete scaffold for GGML_OP_SUM

* naive GGML_OP_SUM kernel

* remove unwanted comment

* change OP_SUM capability gate

* Add has_simdgroup_reduction to both ops to pass CI

webui: updated the chat service to only include max_tokens in the req… (

ggml-org#16489)

* webui: updated the chat service to only include max_tokens in the request payload when the setting is explicitly provided, while still mapping explicit zero or null values to the infinite-token sentinel

* chore: update webui build output

server : fix cancel pending task (ggml-org#16467)

Co-authored-by: DevAI <DevAI@gmail.com>

llama : add --no-host to disable host buffers (ggml-org#16310)

* implement --no-host to disable host buffer

* fix equal_mparams

* move no-host enumeration order together with other model params

---------

Co-authored-by: slaren <slarengh@gmail.com>

CI: reenable cdna in rocm docker builds (ggml-org#16376)

ci: Properly install rocwmma for hip builds (ggml-org#16305)

* CI: Properly install rocwmma for hip builds

on windows we now windows install rocwmma from ubuntu pacakges

* CI: update linux rocm docker build to use rocm 7.0

ggml : implement set_rows with i32 index (ggml-org#16159)

* implement set_rows with i32 index

* template fix

* test quantized path

warnings--

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* forgotten name change

* deduplicate cuda/sycl and test-fix

* indent++

* vulkan: support set_rows with i32 index type (ggml-org#16162)

* disable i32 index for webgpu for now

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (ggml-or…

…g#15797)

* ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type

ggml-backend : add device id to device props

llama : only use iGPU devices if there are no GPU devices

llama : do not use multiple devices from different backends with the same device id

json : support `enum` values within `allOf` (ggml-org#15830)