Skip to content

Releases: ggml-org/llama.cpp

b4958

25 Mar 18:35
@github-actions github-actions
b4958
ef19c71
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4958 Latest
Latest 
run: de-duplicate fmt and format functions and optimize (#11596)
Assets 26

b4957

25 Mar 11:57
@github-actions github-actions
b4957
053b3f9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4957 
ggml-cpu : update KleidiAI to v1.5.0 (#12568)

ggml-cpu : bug fix related to KleidiAI LHS packing

Signed-off-by: Dan Johansson <[email protected]>
Loading

b4956

25 Mar 11:34
@github-actions github-actions
b4956
e2f5601
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4956 
SYCL: disable Q4_0 reorder optimization (#12560)

ggml-ci
Loading

b4953

25 Mar 08:01
@github-actions github-actions
b4953
2d77d88
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4953 
context : fix worst-case reserve outputs (#12545)

ggml-ci
Loading

b4951

24 Mar 17:03
@github-actions github-actions
b4951
2b65ae3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4951 
opencl: simplify kernel embedding logic in cmakefile (#12503)

Co-authored-by: Max Krasnyansky <[email protected]>
Loading

b4948

24 Mar 12:15
@github-actions github-actions
b4948
00d5380
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4948 
llama-vocab : add SuperBPE pre-tokenizer (#12532)
Loading

b4947

24 Mar 11:43
@github-actions github-actions
b4947
7ea7503
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4947 
CUDA: Fix clang warnings (#12540)

Signed-off-by: Xiaodong Ye <[email protected]>
Loading

b4946

24 Mar 11:37
@github-actions github-actions
b4946
c54f6b7
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4946 
mmap : skip resource limit checks on AIX (#12541)
Loading

b4945

24 Mar 07:38
@github-actions github-actions
b4945
9b169a4
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4945 
vulkan: fix mul_mat_vec failure in backend tests (#12529)

The OOB calculation could be wrong if the last iteration was during one of
the unrolled loops. Adjust the unrolling counts to avoid this. Add a couple
new backend tests that hit this failure on NVIDIA GPUs.
Loading

b4944

23 Mar 19:17
@github-actions github-actions
b4944
77f9c6b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b4944 
server : Add verbose output to OAI compatible chat endpoint. (#12246)

Add verbose output to server_task_result_cmpl_final::to_json_oaicompat_chat_stream, making it conform with server_task_result_cmpl_final::to_json_oaicompat_chat, as well as the other to_json methods.
Loading