b2245

kompute : add gemma, phi-2, qwen2, and stablelm to whitelist

Signed-off-by: Jared Van Bortel <[email protected]>

b2023

Early return for zero size calls to get_tensor. (#5482)

* Early return for zero size calls to get_tensor.

Signed-off-by: Adam Treat <[email protected]>

* Update ggml-kompute.cpp

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

* Update ggml-kompute.cpp

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

* Add an early return to the get/set tensor when the size is null.

Signed-off-by: Adam Treat <[email protected]>

* Early return after the assertions.

Signed-off-by: Adam Treat <[email protected]>

* Since we do the early return in the generic backend now no reason to do so here as well.

Signed-off-by: Adam Treat <[email protected]>

---------

Signed-off-by: Adam Treat <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>

b2022

kompute : make partial tensor copies faster by syncing less data (#15)

Signed-off-by: Jared Van Bortel <[email protected]>

b2021

kompute : do not list Intel GPUs as they are unsupported (#14)

Signed-off-by: Jared Van Bortel <[email protected]>

b2020

kompute : disable GPU offload for Mixtral

We haven't implemented the necessary GPU kernels yet.

Fixes this crash:

ggml_vk_graph_compute: error: unsupported op 'ARGSORT'
GGML_ASSERT: /home/jared/src/forks/gpt4all/gpt4all-backend/llama.cpp-mainline/ggml-kompute.cpp:1508: !"unsupported op"

Signed-off-by: Jared Van Bortel <[email protected]>

b2019

common : remove llama_token_to_piece for compatibility with hack

Signed-off-by: Jared Van Bortel <[email protected]>

b1782

Merge branch 'ceb/nomic-vulkan' into nomic

b1780

Merge branch 'ceb/nomic-vulkan' into nomic

b1720

Merge branch 'ceb/nomic-vulkan' into nomic

b1641

kompute : fix -Wunused-private-field warnings from clang

Fixes nomic-ai/gpt4all#1722