 yuiseki
|
5d5c066de8
mtmd : fix Pixtral OOM with large images by capping image_size to 1024 (#14326)
|
7 bulan lalu |
 Sigbjørn Skjæret
|
40bfa04c95
common : use std::string_view now that we target c++17 (#14319)
|
7 bulan lalu |
 Aman Gupta
|
aa064b2eb7
CUDA: add mean operation (#14313)
|
7 bulan lalu |
|
Sigbjørn Skjæret
|
aa0ef5c578
gguf-py : fix Qwen3-Embedding eos token (#14314)
|
7 bulan lalu |
 Markus Tavenrath
|
bb16041cae
Add support for VK_EXT_debug_utils to add labels to Vulkan objects. (#13792)
|
7 bulan lalu |
|
Sigbjørn Skjæret
|
58cba76a9a
gguf-py : fix TemplateProcessing pair when bos/eos is missing (#14312)
|
7 bulan lalu |
 Georgi Gerganov
|
67ae5312e2
metal : fix thread-safety (#14300)
|
7 bulan lalu |
|
Georgi Gerganov
|
692e3cdd0a
memory : rename interface to llama_memory_context_i (#14296)
|
7 bulan lalu |
 Daniel Han
|
b23fa0b3f4
convert : fix Llama 4 conversion (#14311)
|
7 bulan lalu |
|
Georgi Gerganov
|
06cbedfca1
sync : ggml
|
7 bulan lalu |
 Acly
|
b7147673f2
Add `ggml_roll` (ggml/1274)
|
7 bulan lalu |
 David Chiu
|
d860dd99a4
docs : fix the link to llama.h (#14293)
|
7 bulan lalu |
|
Aman Gupta
|
c959f462a0
CUDA: add conv_2d_transpose (#14287)
|
7 bulan lalu |
|
Sigbjørn Skjæret
|
22015b2092
lint : remove trailing whitepace (#14304)
|
7 bulan lalu |
 Ruikai Peng
|
dd6e6d0b6a
vocab : prevent tokenizer overflow (#14301)
|
7 bulan lalu |
 Nicolò Scipione
|
8308f98c7f
sycl: add usage of enqueue_functions extension (#14244)
|
7 bulan lalu |
 Christian Kastner
|
6369be0735
Implement GGML_CPU_ALL_VARIANTS for PowerPC (#14286)
|
7 bulan lalu |
|
Sigbjørn Skjæret
|
88fc854b4b
llama : improve sep token handling (#14272)
|
7 bulan lalu |
 Diego Devesa
|
e28c1b93fd
cuda : synchronize graph capture and cublas handle destruction (#14288)
|
7 bulan lalu |
|
Georgi Gerganov
|
d27b3ca175
ggml : fix repack work size for mul_mat_id (#14292)
|
7 bulan lalu |
 Charles Xu
|
9230dbe2c7
ggml: Update KleidiAI to v1.9.0 (#14277)
|
7 bulan lalu |
|
Georgi Gerganov
|
812939a9e9
model : more uniform output id handling (#14275)
|
7 bulan lalu |
|
Georgi Gerganov
|
4c9fdfbe15
ubatch : new splitting logic (#14217)
|
7 bulan lalu |
|
Aman Gupta
|
9eaa51e7f0
CUDA: add conv_2d_dw (#14265)
|
7 bulan lalu |
|
Diego Devesa
|
8f71d0f3e8
ggml-cpu : remove unnecesary arm feature detection (#14281)
|
7 bulan lalu |
 Alex Trotta
|
381174bbda
gguf-py : make sentencepiece optional (#14200)
|
7 bulan lalu |
 aa956
|
d67341dc18
server : add server parameters for draft model cache type (#13782)
|
7 bulan lalu |
 fanyang
|
456af35eb7
build : suppress gcc15 compile warnings (#14261)
|
7 bulan lalu |
 Anton Mitkov
|
600e3e9b50
sycl: Cleanup codepaths in Get Rows in sycl backend (#14215)
|
7 bulan lalu |
 bashayer hijji
|
fffcce535e
llama-bench : add --no-warmup flag (#14224) (#14270)
|
7 bulan lalu |
