8000 Releases · ochafik/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Releases: ochafik/llama.cpp

b5546

30 May 17:11
@github-actions github-actions
b5546
dd665cc
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
b5546 Latest
Latest 
parallel : increase the variability of the prompt lengths (#13927)

ggml-ci
Assets 18

b5537

29 May 21:49
@github-actions github-actions
b5537
e83ba3e
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
b5537 
llama : add support for jina-reranker-v2 (#13900)
Loading

b5500

26 May 20:41
@github-actions github-actions
b5500
a26c4cc
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
b5500 
scripts : add option to compare commits in Debug (#13806)

* scripts : add option to compare commits in Debug

* cont : reuse existing CMAKE_OPTS
Loading

b5497

26 May 15:34
@github-actions github-actions
b5497
03f582a
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
b5497 
server: fix streaming crashes (#13786)

* add preludes to content on partial regex match

* allow all parsers to parse non-tool-call content.

* tweak order of <|python_tag|> vs <function= parsing for functionary v3.1 format. still not ideal but hopefully less prone to crash
Loading

b5495

26 May 14:22
@github-actions github-actions
b5495
d74e94c
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
b5495 
`server`: fix format of streamed tool call deltas (diff name, fix id …
Loading

b5494

26 May 14:03
@github-actions github-actions
b5494
f13847c
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
b5494 
server: fix regression on streamed non-chat completion w/ stops (#13785)

* more forgiving message diffs: partial stop words aren't erased, full stops are

* Add (slow) server test for completion + stream + stop
Loading

b5493

26 May 11:57
@github-actions github-actions
b5493
79c137f
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
b5493 
examples : allow extracting embeddings from decoder contexts (#13797)

ggml-ci
Loading

b5488

25 May 23:42
@github-actions github-actions
b5488
e121edc
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
b5488 
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3…
Loading

b5479

25 May 07:21
@github-actions github-actions
b5479
7cea29b
Compare
Choose a tag to compare
b5479 
server: fix/test add_generation_prompt
Loading

b5478

25 May 07:18
@github-actions github-actions
b5478
f5cd27b
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
b5478 
`server`: streaming of tool calls and thoughts when `--jinja` is on (…
Loading
0