CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
5,863 Commits 498 Branches 4,731 Tags
b6df0a49d5189bb31cd4716ab731a9ddb7dd57ab
Commit Graph

5863 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
ibrahimkhadraoui
b6df0a49d5 add bos False 2025-07-07 16:57:52 +04:00
ibrahimkhadraoui
ae937f442c rm unused key 2025-07-07 16:57:36 +04:00
ibrahimkhadraoui
53446f7e42 rm unused MAMBA_CHUNK_SIZE 2025-07-07 15:29:56 +04:00
ibrahimkhadraoui
0ad3502839 rm extra space 2025-07-07 15:26:46 +04:00
ibrahim khadraoui
3afb2a89eb Merge pull request #1 from tiiuae/injected-mup 
injected mup
 2025-07-07 15:20:08 +04:00
younesbelkada
e96cc73390 clean ups 2025-07-07 15:13:06 +04:00
younesbelkada
a9f3a63dc1 injected mup 2025-07-07 15:00:25 +04:00
ibrahimkhadraoui
b3bc1fb237 Merge branch 'add-fh1-rebased' of https://github.com/tiiuae/llama.cpp-public into add-fh1-rebased 2025-07-07 14:36:55 +04:00
ibrahimkhadraoui
286e1fa569 fix rope_theta 2025-07-07 14:36:51 +04:00
ibrahimkhadraoui
97011d7a1f mup_vec create as float64 2025-07-07 14:25:32 +04:00
ibrahimkhadraoui
49d7420964 inp_out_ids moved outside of layers loop 2025-07-07 14:18:48 +04:00
ibrahimkhadraoui
8c50893820 added some cb functions for debugging puposes 2025-07-07 14:10:45 +04:00
Younes B
6c39e775dd fix conversion and d_inner 2025-07-07 10:56:49 +02:00
ibrahimkhadraoui
441d8d66bd override modify_tensors instead of get_tensors 2025-07-07 12:00:57 +04:00
ibrahimkhadraoui
53304c84db remove unused functions from gguf_writer.py 2025-07-07 11:18:14 +04:00
ibrahimkhadraoui
c4af0f3ca5 mamba_d_ssm added to d_inner find_hparam 2025-07-07 11:17:31 +04:00
ibrahimkhadraoui
c56ec07a9a read arch from gguf.MODEL_ARCH 2025-07-07 10:34:46 +04:00
ibrahimkhadraoui
280dd2dcb7 falcon-h1 specefic vocab resolved 2025-07-07 10:25:57 +04:00
ibrahimkhadraoui
7a25441e13 fixed multipliers 2025-07-04 17:41:03 +04:00
ibrahimkhadraoui
9760c8bc9d conflict solve 2025-07-04 16:28:48 +04:00
ibrahimkhadraoui
2aa48dd853 Merge branch 'add-fh1-rebased' of https://github.com/tiiuae/llama.cpp-public into add-fh1-rebased 2025-07-04 16:25:54 +04:00
ibrahimkhadraoui
3ee7983961 fix vocab size 2025-07-04 16:25:27 +04:00
younesbelkada
250b4f1074 mix instead of max 2025-07-04 15:53:47 +04:00
younesbelkada
1fd0574adc try 2025-07-04 15:50:43 +04:00
ibrahimkhadraoui
a6d0067dd7 Merge branch 'add-fh1-rebased' of https://github.com/tiiuae/llama.cpp-public into add-fh1-rebased 2025-07-04 15:37:44 +04:00
ibrahimkhadraoui
15138df48f small fix ffn_norm 2025-07-04 15:37:40 +04:00
younesbelkada
6c7d9e26e7 fix 2025-07-04 15:25:59 +04:00
ibrahimkhadraoui
d22b4ea425 Merge branch 'add-fh1-rebased' of https://github.com/tiiuae/llama.cpp-public into add-fh1-rebased 2025-07-04 15:10:11 +04:00
ibrahimkhadraoui
2fe057cc40 Revert "fix" 
This reverts commit 243e4d1a50.
 2025-07-04 15:04:13 +04:00
younesbelkada
22de62cf56 fix 2025-07-04 15:02:14 +04:00
younesbelkada
cce35498d5 pre-norm -> norm 2025-07-04 14:58:33 +04:00
younesbelkada
243e4d1a50 fix 2025-07-04 14:55:31 +04:00
younesbelkada
1415cd8782 another fix 2025-07-04 14:49:59 +04:00
younesbelkada
a39a8423f7 merge 2025-07-04 14:48:22 +04:00
younesbelkada
50eadc7b33 fixes 2025-07-04 14:47:31 +04:00
ibrahimkhadraoui
071f4b7fd8 changed precision for multipliers float 32->64 2025-07-04 14:37:02 +04:00
ibrahimkhadraoui
8bea92261e python fixes 2025-07-04 14:32:11 +04:00
younesbelkada
14c37ec047 more cleaning on python code 2025-07-03 18:09:30 +04:00
younesbelkada
fdd5cff4ba minor fix 2025-07-03 17:12:05 +04:00
younesbelkada
0c93ef6a9c more fixes 2025-07-03 15:26:33 +04:00
younesbelkada
03568c9358 fix 2025-07-03 15:10:18 +04:00
younesbelkada
71a6848e2d another fix 2025-07-03 15:08:23 +04:00
younesbelkada
f897efdaf6 push more fixes 2025-07-03 15:05:01 +04:00
younesbelkada
991de6cbe4 v1 2025-07-03 14:49:56 +04:00
Nicolò Scipione
7b63a71a6b Fix conditional enabling following arch checks for ggml-sycl (#14504) 
Signed-off-by: nscipione <nicolo.scipione@codeplay.com>
b5819 		2025-07-03 11:00:03 +02:00
Xuan-Son Nguyen
0c2ee38ab7 convert : correct gemma 3n conversion (#14450) 
* convert : correct gemma 3n conversion

* rm redundant code
 2025-07-03 10:03:06 +02:00
Georgi Gerganov
a70c8a0c4b kv-cache : use ggml_set_rows (#14285) 
* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci
b5817 		2025-07-03 10:53:35 +03:00
Georgi Gerganov
9067487c44 ggml : fix FA mask dim 2 and 3 (#14505) 
* ggml : fix FA mask dim 2 and 3

ggml-ci

* backends : unsupport batched FA in CUDA and Vulkan

ggml-ci

* vulkan : disable FA for mask->ne[2] != 1
b5816 		2025-07-03 10:46:57 +03:00
Georgi Gerganov
d4cdd9c1c3 ggml : remove kompute backend (#14501) 
ggml-ci
b5815 		2025-07-03 07:48:32 +03:00
Aman Gupta
55c2646b45 CUDA: add dynamic shared mem to softmax, refactor general usage (#14497) b5814 2025-07-03 07:45:11 +08:00