 Jeff Bolz
|
c4f53563df
vulkan: support fattn sinks (#15126)
|
5 달 전 |
|
Jeff Bolz
|
a0552c8bee
vulkan: Add env var to disable host visible vidmem (#15109)
|
5 달 전 |
 RunningLeon
|
99acbc9921
llama : Support intern-s1 (#14875)
|
5 달 전 |
 uvos
|
7ad67ba9fe
HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103)
|
5 달 전 |
 Christian Kastner
|
9a96389544
ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)
|
5 달 전 |
 Johannes Gäßler
|
1d72c84188
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131)
|
5 달 전 |
|
Johannes Gäßler
|
20638e4f16
scripts: fix crash when --tool is not set (#15133)
|
5 달 전 |
 Daniel Bevenius
|
36d3f00e14
requirements : fix PyTorch uint64 compatibility (#15134)
|
5 달 전 |
 Reese Levine
|
5fd160bbd9
ggml: Add basic SET_ROWS support in WebGPU (#15137)
|
5 달 전 |
 rmatif
|
756cfea826
fix profiling crash (#15072)
|
5 달 전 |
 lhez
|
e725a1a982
opencl: add `swiglu_oai` and `add_id` (#15121)
|
5 달 전 |
 Sachin Desai
|
3db4da56a5
chat : support Granite model reasoning and tool call (#14864)
|
5 달 전 |
 Juk Armstrong
|
476aa3fd57
Fixed name `-override-tensors` to `-override-tensor` (#15129)
|
5 달 전 |
 Diego Devesa
|
0d8831543c
ggml : fix fallback to CPU for ununsupported ops (#15118)
|
5 달 전 |
 Sigbjørn Skjæret
|
65c797c4fa
chat : fix yandex chat template (#15116)
|
5 달 전 |
 stevenkuang
|
25726898e8
chat : fix hunyuan auto-detection (#15114)
|
5 달 전 |
 Chenguang Li
|
2241453252
CANN: add support for ACL Graph (#15065)
|
5 달 전 |
|
Reese Levine
|
9515c6131a
ggml: WebGPU disable SET_ROWS for now (#15078)
|
5 달 전 |
 Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 달 전 |
|
Sigbjørn Skjæret
|
f324a3b715
chat : only remove double bos/eos if added (#15086)
|
5 달 전 |
|
Georgi Gerganov
|
be42642581
readme : update hot topics (#15097)
|
5 달 전 |
 Romain Biessy
|
3306ceabf0
sycl: fix mul_mat selection (#15092)
|
5 달 전 |
|
Juk Armstrong
|
c81de6e107
Fix `glm4moe` bug (#15088)
|
5 달 전 |
 Alex Wu
|
22f060c9c4
webui: fix markdown table (#15081)
|
5 달 전 |
 compilade
|
ee3a9fcf88
context : fix index overflow on huge outputs (#15080)
|
5 달 전 |
|
Diego Devesa
|
ec428b02c3
llama : add --n-cpu-moe option (#15077)
|
5 달 전 |
|
compilade
|
19f68fa5a4
imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)
|
5 달 전 |
|
Christian Kastner
|
41613437ff
cmake: Add GGML_BACKEND_DIR option (#15074)
|
5 달 전 |
|
Sigbjørn Skjæret
|
e5bebe5251
gguf-py : add --chat-template-file to gguf_new_metadata (#15075)
|
5 달 전 |
 Sam
|
ef0144c087
model: support GLM 4.5 family of models (#14939)
|
5 달 전 |
