Skip to content

Releases: wangqi/llama.cpp

b6301

27 Aug 19:38
da54f9f
Compare
Choose a tag to compare
presets : add qwen3-30B-a3b FIM (#15616)

b6133

11 Aug 15:36
cf9e564
Compare
Choose a tag to compare
mtmd : Fix MinicpmV model converter and clip to avoid using hardcode.…

b5952

21 Jul 14:39
9220426
Compare
Choose a tag to compare
kleidiai: add support for get_rows (#14676)

* kleidiai: add support for get_rows

* apply fixes based on code review

* apply more fixes based on code review

b5897

14 Jul 18:57
bdca383
Compare
Choose a tag to compare
sycl: Hotfix for non dnnl codepath (#14677)

b5848

08 Jul 18:34
699f439
Compare
Choose a tag to compare
model : fix hunyuan moe chat template (#14584)

Signed-off-by: stevenkuang <[email protected]>

b5349

11 May 18:41
9a390c4
Compare
Choose a tag to compare
tools : fix uninitialized llama_batch in server (#13436)

* add constructor to initialize server_context::batch, preventing destructor's call to llama_batch_free from causing an invalid free()

* Update tools/server/server.cpp

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

* use C++11 initializer syntax

* switch from Copy-list-initialization to Direct-list-initialization

---------

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

b5054

05 Apr 04:33
7a84777
Compare
Choose a tag to compare
sync: minja (#12739)

* sync: minja

https://github.com/google/minja/pull/57

* fix json include

b4848

07 Mar 10:51
7cf64f6
Compare
Choose a tag to compare
sync: minja - support QwQ-32B (#12235)

https://github.com/google/minja/commit/8a76f7815e8a3ae00bd233c2b5a8b7d4e86564ec

b4847

07 Mar 08:44
5e2d57b
Compare
Choose a tag to compare
metal : simplify kernel arguments using a struct (#3229) (#12194)

* metal : refactor im2col parameters into a struct

* metal: Change im2col offset types from int32_t to uint64_t to support larger memory offsets

* metal : refactor sum_rows parameters into a struct

* metal : refactor soft_max parameters into a struct

* metal : refactor diag_mask_inf parameters into a struct

* metal : refactor ssm_conv parameters into a struct

* metal : refactor ssm_scan parameters into a struct

* metal : refactor get_rows parameters into a struct

* metal : refactor group_norm parameters into a struct

* metal : refactor conv_transpose_1d parameters into a struct

* metal : refactor upscale parameters into a struct

* metal : refactor pad parameters into a struct

* metal : refactor pad_reflect_1d parameters into a struct

* metal : refactor arange parameters into a struct

* metal : refactor timestep_embedding parameters into a struct

* metal : refactor argsort parameters into a struct

* metal : refactor leaky_relu parameters into a struct

* metal : refactor pool_2d parameters into a struct

* metal : fix trailing whitespace

---------

Co-authored-by: alexju <[email protected]>

b4820

04 Mar 09:58
1a24c46
Compare
Choose a tag to compare
`server`: fix deadly typo in response_format.json_schema.schema handl…