 Kai Pastor
|
60f816a79d
cmake : fix usage issues (ggml/1257)
|
6 months ago |
 Daniel Bevenius
|
5592f278b6
ggml-cpu : remove stdlib include from repack.cpp (ggml/1276)
|
6 months ago |
 Georgi Gerganov
|
e4868d16d2
context : perform output reorder lazily upon access after sync (#14853)
|
6 months ago |
 Xuan-Son Nguyen
|
820de57d4f
chat : fix kimi-k2 chat template (#14852)
|
6 months ago |
 Alberto Cabrera Pérez
|
cb4a63aad6
sycl: fixed semantics of block offset calculation (#14814)
|
6 months ago |
 yummy
|
86f5623d90
llama : fix MiniCPM inference after Granite Four changes (#14850)
|
6 months ago |
 Pouya
|
39cffdf188
docs: add libcurl-dev install hint for Linux distros (#14801)
|
6 months ago |
|
Georgi Gerganov
|
065908cb09
metal : fix fusion across different encoders (#14849)
|
6 months ago |
 Donghyeon Jeong
|
4ec6291a24
sycl: fix undefined variable in work group size check (#14843)
|
6 months ago |
 jacekpoplawski
|
a12363bbf0
convert : text-only support for GLM-4.1V-9B-Thinking (#14823)
|
6 months ago |
 Johannes Gäßler
|
a86f52b285
CUDA: fix overflow in FA, tune performance (#14840)
|
6 months ago |
|
Johannes Gäßler
|
b284197df4
CUDA: fix compilation with GGML_CUDA_F16 (#14837)
|
6 months ago |
 Sigbjørn Skjæret
|
221c0e0c58
ci : correct label refactor->refactoring (#14832)
|
6 months ago |
|
Johannes Gäßler
|
07a19e27a2
CUDA: fix quantized KV cache + multiple sequences (#14822)
|
6 months ago |
|
Georgi Gerganov
|
18f3b5ff9e
tests : add non-cont K,V FA tests
|
6 months ago |
 l3utterfly
|
7233358d29
memory : handle saving/loading null layers in recurrent memory (#14675)
|
6 months ago |
 lixing-star
|
6c88b3bb25
ggml: fix loongarch quantize_row_q8_1 error (#14827)
|
6 months ago |
 chen fan
|
14c28dfc50
CANN: weight format to NZ for Ascend310P3 (#14407)
|
6 months ago |
 Aman Gupta
|
8c988fa41d
CUDA: add fused rms norm (#14800)
|
6 months ago |
 Csaba Kecskemeti
|
acd6cb1c41
ggml : model card yaml tab->2xspace (#14819)
|
6 months ago |
 Jeff Bolz
|
84712b6043
vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817)
|
6 months ago |
 Molly Sophia
|
d4d1522b20
llama : add model type detection for rwkv7 7B&14B (#14816)
|
6 months ago |
 Ed Addario
|
d1aa0cc5d1
imatrix: add option to display importance score statistics for a given imatrix file (#12718)
|
6 months ago |
 stduhpf
|
c8ade30036
Mtmd: add a way to select device for vision encoder (#14236)
|
6 months ago |
|
Sigbjørn Skjæret
|
e28c0b80c2
cuda : implement bf16 cpy ops and enable bf16 cont (#14763)
|
6 months ago |
 lhez
|
8e6f8bc875
opencl: remove unreachable `return` (#14806)
|
6 months ago |
|
Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
6 months ago |
 R0CKSTAR
|
48b86c4fdb
cuda: remove linking to cublasLt (#14790)
|
6 months ago |
|
Sigbjørn Skjæret
|
38d3af1b73
opencl: fix `im2col` when `KW!=KH` (#14803)
|
6 months ago |
 rmatif
|
6c9ee3b17e
opencl: add conv2d kernel (#14403)
|
6 months ago |
