llama.cpp
SYCL: Implement few same quantized type copy kernels
#13739

Merged

SYCL: Implement few same quantized type copy kernels #13739

qnixsynapse merged 6 commits into master from sycl/same_q_cpy

qnixsynapse marked this pull request as draft 206 days ago

github-actions added ggml

github-actions added SYCL

qnixsynapse marked this pull request as ready for review 205 days ago

Rbiessy commented on 2025-05-26

qnixsynapse marked this pull request as draft 202 days ago

qnixsynapse force pushed to 3cdc64b9 202 days ago

qnixsynapse force pushed from 3cdc64b9 to c8c22786 199 days ago

qnixsynapse marked this pull request as ready for review 196 days ago

qnixsynapse requested a review from

Alcpz 195 days ago

SYCL: Implement few same quantized type copy kernels

c26934dd

Use memcpy for copying contiguous tensors

608e8811

feat(sycl): add contiguous tensor copy support and device checks

faeb7f34

refactor: replace specific block copy functions with template

b36c550d

Exclude BF16 support for COPY tensors for now

b6db0056

qnixsynapse force pushed to b6db0056 195 days ago

Rbiessy commented on 2025-06-03

perf: adjust SYCL copy kernel block sizes for efficiency

4aa261af

Rbiessy approved these changes on 2025-06-06

qnixsynapse merged 228f34c9 into master 191 days ago

qnixsynapse deleted the sycl/same_q_cpy branch 191 days ago

Reviewers

Rbiessy

Alcpz

Assignees

No one assigned

Labels

ggml SYCL

Milestone

No milestone