Skip to content

Releases: fairydreaming/llama.cpp

b4543

24 Jan 13:33
8137b4b
Compare
Choose a tag to compare
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380)

b4528

22 Jan 17:15
c64d2be
Compare
Choose a tag to compare
`minja`: sync at https://github.com/google/minja/commit/0f5f7f2b3770e…

b4524

21 Jan 18:39
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]>

b4410

03 Jan 19:49
4b0c638
Compare
Choose a tag to compare
common : disable KV cache shifting automatically for unsupported mode…

b4405

02 Jan 09:43
a45433b
Compare
Choose a tag to compare
readme : add llama-swap to infrastructure section (#11032)

* list llama-swap under tools in README

* readme: add llama-swap to Infrastructure

b4323

13 Dec 18:36
11e07fd
Compare
Choose a tag to compare
fix: graceful shutdown for Docker images (#10815)

b4255

03 Dec 20:55
cc98896
Compare
Choose a tag to compare
vulkan: optimize and reenable split_k (#10637)

Use vector loads when possible in mul_mat_split_k_reduce. Use split_k
when there aren't enough workgroups to fill the shaders.

b4219

29 Nov 13:17
266b851
Compare
Choose a tag to compare
sycl : Reroute permuted mul_mats through oneMKL (#10408)

This PR fixes the failing MUL_MAT tests for the sycl backend.

b3605

19 Aug 19:12
cfac111
Compare
Choose a tag to compare
cann: add doc for cann backend (#8867)

Co-authored-by: xuedinge233 <[email protected]>
Co-authored-by: hipudding <[email protected]>

b3357

09 Jul 20:54
fd560fe
Compare
Choose a tag to compare
Update README.md to fix broken link to docs (#8399)

Update the "Performance troubleshooting" doc link to be correct - the file was moved into a dir called 'development'