Skip to content

Releases: ggerganov/llama.cpp

b4529

22 Jan 17:45
12c2bdf
Compare
Choose a tag to compare
server : fix draft context not being released (#11354)

b4528

22 Jan 17:14
c64d2be
Compare
Choose a tag to compare
`minja`: sync at https://github.com/google/minja/commit/0f5f7f2b3770e…

b4527

22 Jan 12:34
96f4053
Compare
Choose a tag to compare
Adding logprobs to /v1/completions (#11344)

Signed-off-by: Jiri Podivin <[email protected]>

b4526

22 Jan 10:40
a94f3b2
Compare
Choose a tag to compare
`common`: utils to split / join / repeat strings (from json converter…

b4525

22 Jan 08:15
3e3357f
Compare
Choose a tag to compare
llava : support Minicpm-omni (#11289)

* init

* add readme

* update readme

* no use make

* update readme

* update fix code

* fix editorconfig-checker

* no change convert py

* use clip_image_u8_free

b4524

21 Jan 15:00
6171c9d
Compare
Choose a tag to compare
Add Jinja template support (#11016)

* Copy minja from https://github.com/google/minja/commit/58f0ca6dd74bcbfbd4e71229736640322b31c7f9

* Add --jinja and --chat-template-file flags

* Add missing <optional> include

* Avoid print in get_hf_chat_template.py

* No designated initializers yet

* Try and work around msvc++ non-macro max resolution quirk

* Update test_chat_completion.py

* Wire LLM_KV_TOKENIZER_CHAT_TEMPLATE_N in llama_model_chat_template

* Refactor test-chat-template

* Test templates w/ minja

* Fix deprecation

* Add --jinja to llama-run

* Update common_chat_format_example to use minja template wrapper

* Test chat_template in e2e test

* Update utils.py

* Update test_chat_completion.py

* Update run.cpp

* Update arg.cpp

* Refactor common_chat_* functions to accept minja template + use_jinja option

* Attempt to fix linkage of LLAMA_CHATML_TEMPLATE

* Revert LLAMA_CHATML_TEMPLATE refactor

* Normalize newlines in test-chat-templates for windows tests

* Forward decl minja::chat_template to avoid eager json dep

* Flush stdout in chat template before potential crash

* Fix copy elision warning

* Rm unused optional include

* Add missing optional include to server.cpp

* Disable jinja test that has a cryptic windows failure

* minja: fix vigogne (https://github.com/google/minja/pull/22)

* Apply suggestions from code review

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

* Finish suggested renamings

* Move chat_templates inside server_context + remove mutex

* Update --chat-template-file w/ recent change to --chat-template

* Refactor chat template validation

* Guard against missing eos/bos tokens (null token otherwise throws in llama_vocab::impl::token_get_attr)

* Warn against missing eos / bos tokens when jinja template references them

* rename: common_chat_template[s]

* reinstate assert on chat_templates.template_default

* Update minja to https://github.com/google/minja/commit/b8437df626ac6cd0ce3b333b3c74ed1129c19f25

* Update minja to https://github.com/google/minja/pull/25

* Update minja from https://github.com/google/minja/pull/27

* rm unused optional header

---------

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

b4523

21 Jan 14:59
e28245f
Compare
Choose a tag to compare
export-lora : fix tok_embd tensor (#11330)

b4522

21 Jan 14:49
6da5bec
Compare
Choose a tag to compare
rpc : better caching of the base buffer pointer (#11331)

There is no need to use map, just store the base pointer in the buffer
context.

b4521

21 Jan 10:04
2e2f8f0
Compare
Choose a tag to compare
linenoise.cpp refactoring (#11301)

More RAII mainly

Signed-off-by: Eric Curtin <[email protected]>

b4520

21 Jan 07:29
2139667
Compare
Choose a tag to compare
metal : fix out-of-bounds write (#11314)

ggml-ci