 Sigbjørn Skjæret
|
eff5e45443
add GELU_ERF (#14455)
|
6 months ago |
 Georgi Gerganov
|
a6a47958a1
ggml : remove trailing whitespace (#0)
|
6 months ago |
|
Georgi Gerganov
|
f61c05d4b1
sync : ggml
|
6 months ago |
 Acly
|
431b2c24f3
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
|
6 months ago |
 Daniel Bevenius
|
497be7c01d
ggml-quants : rename best_mad to best_error (ggml/1283)
|
7 months ago |
 lhez
|
79b33b2317
opencl : add GEGLU, REGLU, SWIGLU (#14456)
|
6 months ago |
 Aman Gupta
|
0a5a3b5cdf
Add Conv2d for CPU (#14388)
|
6 months ago |
|
Georgi Gerganov
|
745f11fed0
memory : correctly handle failure in apply() (#14438)
|
6 months ago |
|
Georgi Gerganov
|
5dd942de59
metal : disable fast-math for some cpy kernels (#14460)
|
6 months ago |
 Romain Biessy
|
a7417f5594
ggml-cpu: sycl: Re-enable exp f16 (#14462)
|
6 months ago |
 Diego Devesa
|
eb3fa2913e
test-backend-ops : disable llama test (#14461)
|
6 months ago |
 xiaobing318
|
c839a2da1a
cmake : Remove redundant include path in CMakeLists.txt (#14452)
|
6 months ago |
 Vedran Miletić
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
6 months ago |
 matteo
|
caf5681fcb
server : support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client (#13196)
|
6 months ago |
 Renat
|
83790b0e7e
server : fix appearance of the chats list context menu for Safari (#14322)
|
6 months ago |
 Akarshan Biswas
|
f47c1d7106
SYCL: disable faulty fp16 exp kernel (#14395)
|
6 months ago |
|
Sigbjørn Skjæret
|
a5d1fb6212
ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (#14443)
|
6 months ago |
|
Sigbjørn Skjæret
|
a0535ffa0d
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)
|
6 months ago |
 Jeff Bolz
|
bd9c981d72
vulkan: Add fusion support for RMS_NORM+MUL (#14366)
|
6 months ago |
|
Aman Gupta
|
27208bf657
CUDA: add bf16 and f32 support to cublas_mul_mat_batched (#14361)
|
6 months ago |
|
Jeff Bolz
|
63a7bb3c7e
vulkan: handle noncontig in the final case of ggml_vk_get_cpy_pipeline (#14378)
|
6 months ago |
|
Jeff Bolz
|
00d5282c7f
vulkan: lock accesses of pinned_memory vector (#14333)
|
6 months ago |
 Weizhao Ouyang
|
566c16fcce
model : add support for ERNIE 4.5 0.3B model (#14408)
|
6 months ago |
 Xinpeng Dou
|
b25e92774e
fix async_mode bug (#14432)
|
6 months ago |
|
Sigbjørn Skjæret
|
6609507a91
ci : fix windows build and release (#14431)
|
6 months ago |
|
Jeff Bolz
|
ceb1bf5a34
vulkan: Fix GGML_VULKAN_SHADER_DEBUG_INFO (#14427)
|
6 months ago |
|
Georgi Gerganov
|
72babea5de
graph : make llm_graph_context destructor virtual (#14410)
|
6 months ago |
|
Georgi Gerganov
|
43678060c1
recurrent : call balloc split_reset() in init_batch() (#14414)
|
6 months ago |
 Radoslav Gerganov
|
8d94219a4a
ggml : add ggml_set_rows (#14274)
|
6 months ago |
|
Sigbjørn Skjæret
|
f667f1e624
convert : fix broken sentencepiece vocab (#14416)
|
6 months ago |
