Skip to content

Releases: teleprint-me/llama.cpp

b2972

23 May 04:38
cd93a28
Compare
Choose a tag to compare
CUDA: fix FA out-of-bounds reads (#7479)

b2970

22 May 18:09
197ff91
Compare
Choose a tag to compare
build : remove zig (#7471)

b2961

21 May 21:56
201cc11
Compare
Choose a tag to compare
llama : add phi3 128K model support (#7225)

* add phi3 128k support in convert-hf-to-gguf

* add phi3 128k support in cuda

* address build warnings on llama.cpp

* adjust index value in cuda long rope freq factors

* add long rope support in ggml cpu backend

* make freq factors only depend on ctx size

* remove unused rope scaling type 'su' frin gguf converter

* fix flint warnings on convert-hf-to-gguf.py

* set to the short freq factor when context size is small than trained context size

* add one line of comments

* metal : support rope freq_factors

* ggml : update ggml_rope_ext API to support freq. factors

* backends : add dev messages to support rope freq. factors

* minor : style

* tests : update to use new rope API

* backends : fix pragma semicolons

* minor : cleanup

* llama : move rope factors from KV header to tensors

* llama : remove tmp assert

* cuda : fix compile warning

* convert : read/write n_head_kv

* llama : fix uninitialized tensors

---------

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

b2958

21 May 18:54
fcf6538
Compare
Choose a tag to compare
CUDA: fix unused warning in mmq.cu (#7442)

b2953

20 May 19:25
917dc8c
Compare
Choose a tag to compare
Tokenizer SPM fixes for phi-3 and llama-spm (#7375)

* Update brute force test: special tokens
* Fix added tokens
  - Try to read 'added_tokens.json'.
  - Try to read 'tokenizer_config.json'.
  - Try to read 'tokenizer.json'.
* Fix special tokens rtrim

Co-authored-by: Georgi Gerganov <[email protected]>
* server : fix test regexes

b2941

20 May 04:00
33c8d50
Compare
Choose a tag to compare
Add provisions for windows support for BF16 code including CMake prov…

b2939

19 May 20:31
1ea2a00
Compare
Choose a tag to compare
quantize : fix --keep-split check (#7374)

b2929

19 May 03:06
f5bf761
Compare
Choose a tag to compare
Capture CUDA logging output (#7298)

* logging: output capture in cuda module

* fix compile error

* fix: vsnprintf terminates with 0, string use not correct

* post review

* Update llama.cpp

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

* Update llama.cpp

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

---------

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

b2916

17 May 23:50
b43272a
Compare
Choose a tag to compare
Unicode codepoint flags for custom regexs (#7245)

* Replace CODEPOINT_TYPE_* with codepoint_flags
* Update and bugfix brute force random test
* Deterministic brute force random test
* Unicode normalization NFD
* Get rid of BOM

b2915

17 May 22:35
0fc1e82
Compare
Choose a tag to compare
CUDA: faster large batch FA without tensor cores (#7314)