 Xuan-Son Nguyen
|
5fa9e63be8
clip : refactor set input for cgraph + fix qwen2.5vl input (#13136)
|
8 months ago |
 Akarshan Biswas
|
a4c340f974
SYCL: Add all missing unary kernels (#13074)
|
8 months ago |
 Georgi Gerganov
|
d0a417f3c7
readme : update hot topics (#13150)
|
8 months ago |
|
Georgi Gerganov
|
43f2b07193
common : fix noreturn compile warning (#13151)
|
8 months ago |
|
Xuan-Son Nguyen
|
e5d6c2554e
llama-chat : fix typo GML --> GLM (#13143)
|
8 months ago |
 R0CKSTAR
|
f0dd6a1926
musa: fix typo in cc control (#13144)
|
8 months ago |
 Johannes Gäßler
|
69699be48a
CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (#13137)
|
8 months ago |
|
Xuan-Son Nguyen
|
85f36e5e71
arg : fix unused variable (#13142)
|
8 months ago |
 4onen
|
c0a97b762e
llama-bench : Add `--override-tensors` arg (#12922)
|
8 months ago |
 matteo
|
ced44be342
llama-chat : fix wrong template in GLM4-0414 (#13140)
|
8 months ago |
|
R0CKSTAR
|
e291450b76
musa: fix build warning (#13129)
|
8 months ago |
 LostRuins Concedo
|
59e991c23c
Fixes Qwen2.5VL segfault during inference with https://github.com/ggml-org/llama.cpp/pull/12402 as has_qwen2vl_merger migration was incomplete (#13133)
|
8 months ago |
 HimariO
|
ca2bb89eac
clip : Add Qwen2.5VL support (#12402)
|
8 months ago |
|
Xuan-Son Nguyen
|
2d451c8059
common : add common_remote_get_content (#13123)
|
8 months ago |
|
Xuan-Son Nguyen
|
4753791e70
clip : improve projector naming (#13118)
|
8 months ago |
 SXX
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
8 months ago |
 frob
|
d5fe4e81bd
grammar : handle maxItems == 0 in JSON schema (#13117)
|
9 months ago |
 Diego Devesa
|
295354ea68
llama : fix K-shift with quantized K and BLAS backend (#13113)
|
9 months ago |
 City
|
558a764713
Force FP32 compute in GLM4 FFN Down (#13101)
|
9 months ago |
|
Xuan-Son Nguyen
|
edb18b6e8f
clip : fix pixtral on some GPU backends (#13097)
|
9 months ago |
 Neo Zhang Jianyu
|
514c45608f
change the reorder tensor from init to execute OP (#13003)
|
9 months ago |
 Radoslav Gerganov
|
553a5c3a9f
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)
|
9 months ago |
|
Xuan-Son Nguyen
|
13be08daf9
clip : remove boi/eoi embeddings for GLM-edge model (#13081)
|
9 months ago |
|
Georgi Gerganov
|
226251ed56
embeddings : fix batch sizes (#13076)
|
9 months ago |
|
Georgi Gerganov
|
87616f0680
ggml : fix trailing whitespaces (#0)
|
9 months ago |
|
Georgi Gerganov
|
63b4911494
sync : ggml
|
9 months ago |
 Acly
|
c6e8cc28c1
ggml : Depthwise 2D convolution (ggml/1152)
|
9 months ago |
|
Johannes Gäßler
|
b10d8bfdb1
CUDA: use switch statements in constexpr functions (#13095)
|
9 months ago |
|
Georgi Gerganov
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
9 months ago |
|
Georgi Gerganov
|
572b3141d3
clang-tidy : disable warning about missing math parenthesis (#13091)
|
9 months ago |
