Ed Addario
|
c81f4192f9
gguf-py : dump bpw per layer and model in markdown mode (#14703)
|
6 сар өмнө |
Gabriel Larson
|
4a4f426944
model : add Kimi-K2 support (#14654)
|
6 сар өмнө |
Jeff Bolz
|
ba1ceb3456
vulkan: fix noncontig check for mat_mul_id splitting (#14683)
|
6 сар өмнө |
Jeff Bolz
|
10a0351a97
vulkan: add RTE variants for glu/add/sub/mul/div (#14653)
|
6 сар өмнө |
Shunta Saito
|
68e37a61a7
model : add PLaMo-2 support (#14560)
|
6 сар өмнө |
R0CKSTAR
|
cbc68be51d
cuda: fix build warnings in set-rows.cu (unused variable) (#14687)
|
6 сар өмнө |
Anton Mitkov
|
bdca38376f
sycl: Hotfix for non dnnl codepath (#14677)
|
6 сар өмнө |
shalinib-ibm
|
55c509daf5
ggml : refactor llamafile_sgemm PPC code (#14673)
|
6 сар өмнө |
Aman Gupta
|
9c9e4fc635
llama-context: add ability to get logits (#14672)
|
6 сар өмнө |
Johannes Gäßler
|
494c5899cb
scripts: benchmark for HTTP server throughput (#14668)
|
6 сар өмнө |
Akarshan Biswas
|
0f4c6ec0f1
SYCL: use 1D kernel for set_rows (#14618)
|
6 сар өмнө |
Anton Mitkov
|
65a3ebb0aa
sycl: Batched mulmat rework for oneDNN dispatch (#14617)
|
6 сар өмнө |
Molly Sophia
|
0d9226763c
llama : add jinja template for rwkv-world (#14665)
|
6 сар өмнө |
Ed Addario
|
982e347255
quantize : fix minor logic flaw in --tensor-type (#14572)
|
6 сар өмнө |
Sigbjørn Skjæret
|
923e3ea2e3
cuda : add set rows for bf16 (#14664)
|
6 сар өмнө |
Yavor Ivanov
|
e743cddb60
cuda : add ELU support (#14657)
|
6 сар өмнө |
Georgi Gerganov
|
05fec5bd29
ggml : add build-time message to remind about ggml_set_rows (#14661)
|
6 сар өмнө |
Yavor Ivanov
|
dcf7f2ea3c
metal : Add missing unary ops Metal support (#14660)
|
6 сар өмнө |
Yavor Ivanov
|
84b396e051
cmake : Add CMake presets for Linux and GCC (#14656)
|
6 сар өмнө |
Tarek Dakhran
|
c31e60647d
tests : cover lfm2 cases in test_ssm_conv (#14651)
|
6 сар өмнө |
Tarek Dakhran
|
67eade1bf9
docs : add LFM2 to models section (#14650)
|
6 сар өмнө |
Aman Gupta
|
7de5c7cab6
CUDA: add set rows for f32 and f16 (#14551)
|
6 сар өмнө |
Georgi Gerganov
|
8eff95544e
sync : ggml
|
6 сар өмнө |
Georgi Gerganov
|
3120413ccd
vulkan : remove unused vars (#0)
|
6 сар өмнө |
Georgi Gerganov
|
215535701d
sync : ggml
|
6 сар өмнө |
Acly
|
74bb294591
vulkan : implement bilinear interpolation (ggml/1291)
|
6 сар өмнө |
Acly
|
3e303b1107
vulkan : implement ggml_roll (ggml/1290)
|
6 сар өмнө |
Douglas Hanley
|
0c1df14b5f
server : fix pooled embedding output (#14645)
|
6 сар өмнө |
Jeff Bolz
|
b3ad3a0191
vulkan: support SET_ROWS (#14587)
|
6 сар өмнө |
Jeff Bolz
|
98197e5c98
vulkan: optimizations for deepseek prompt processing (#14555)
|
6 сар өмнө |