Skip to content

Releases: ggml-org/llama.cpp

b4371

20 Dec 16:12
eb5c3dc
Compare
Choose a tag to compare
SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)

* Migrate to tensor->buffer for checking backend buffer type: 1

* SYCL: common.cpp try to migrate away from tensor->backend

* SYCL: fix assertions and add proper comments

* SYCL: remove extra space

* SYCL: Add back static to ggml_backend_buffer_is_sycl_split function

* SYCL: Add pragma directive to suppress warning spam

* SYCL: Integrate debug logs with GGML_LOG and other fixes

* Revert "SYCL: Integrate debug logs with GGML_LOG and other fixes"

This reverts commit 2607b7de0f0d2f4f1f690226f86fa861aa39cb97.
Let's keep the current SYCL specific logging mechanism for now

* SYCL: Use GGML_SYCL_DEBUG after reverting

* SYCL: reg_get_proc_address func, update to the current func signature

* SYCL: Refactor SYCL buffer checks in ggml_sycl_cpy_tensor_2d

b4369

20 Dec 13:32
21ae3b9
Compare
Choose a tag to compare
ggml : add test for SVE and disable when it fails (#10906)

b4368

20 Dec 10:24
0a11f8b
Compare
Choose a tag to compare
convert : fix RWKV v6 model conversion (#10913)

* Enable --no-context-shift for llama-perplexity example

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

* RWKV 6: Fix error in ggml_cuda_op_bin_bcast

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

---------

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

b4367

19 Dec 17:43
d408bb9
Compare
Choose a tag to compare
clip : disable GPU support (#10896)

ggml-ci

b4366

19 Dec 17:18
5cab3e4
Compare
Choose a tag to compare
llama : minor grammar refactor (#10897)

ggml-ci

b4365

19 Dec 16:39
36319de
Compare
Choose a tag to compare
tts : small QoL for easy model fetch (#10903)

b4363

19 Dec 14:13
a3c33b1
Compare
Choose a tag to compare
ggml: fix arm build with gcc (#10895)

Signed-off-by: Adrien Gallouët <[email protected]>

b4362

19 Dec 14:00
2fffc52
Compare
Choose a tag to compare
llama : fix Roberta embeddings (#10856)

* fix: Use gpt2 tokenizer for roberta and add eos/bos tokens

Branch: RobertaTokenizer

Signed-off-by: Gabe Goodhart <[email protected]>

* fixes to position embeddings

Signed-off-by: Sukriti-Sharma4 <[email protected]>

* map roberta-bpe to gpt-2

Signed-off-by: Sukriti-Sharma4 <[email protected]>

* fix linting

Signed-off-by: Sukriti-Sharma4 <[email protected]>

---------

Signed-off-by: Gabe Goodhart <[email protected]>
Signed-off-by: Sukriti-Sharma4 <[email protected]>
Co-authored-by: Gabe Goodhart <[email protected]>

b4361

19 Dec 10:15
7585edb
Compare
Choose a tag to compare
convert : Add support for Microsoft Phi-4 model  (#10817)

* convert : use GPT2 vocab for Phi-4 model

* convert : use null value of sliding_window to distinguish Phi-4 from other PHI3-based models

* llama : do not use sliding window attention mask for Phi-4 model

---------

Co-authored-by: Stanisław Szymczyk <[email protected]>

b4360

19 Dec 08:40
cd920d0
Compare
Choose a tag to compare
tests: disable GGUF test for bad value size (#10886)