 Diego Devesa
|
9f2da5871f
llama : build windows releases with dl backends (#13220)
|
8 ماه پیش |
 Johannes Gäßler
|
93c4e23905
CUDA: fix race condition in MMQ stream-k fixup (#13299)
|
8 ماه پیش |
|
Johannes Gäßler
|
8afbd96818
CUDA: fix race condition in MMQ ids_dst (#13294)
|
8 ماه پیش |
 Jeff Bolz
|
8ae5ebcf85
vulkan: Additional type support for unary, binary, and copy (#13266)
|
8 ماه پیش |
|
Johannes Gäßler
|
3e959f0976
imatrix: fix oob writes if src1 is not contiguous (#13286)
|
8 ماه پیش |
 Xuan-Son Nguyen
|
36667c8edc
clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking change) (#13259)
|
8 ماه پیش |
 ymcki
|
3bf785f3ef
llama : Llama-3_1-Nemotron-Ultra-253B-v1 support (#12843)
|
8 ماه پیش |
|
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 ماه پیش |
 Georgi Gerganov
|
b34443923c
sync : ggml (#13268)
|
8 ماه پیش |
|
Georgi Gerganov
|
a75cb30dc9
context : fix reorder logic (#13267)
|
8 ماه پیش |
 shalinib-ibm
|
3f3769ba76
ggml : Enable MMA for BF16 in llamafile_sgemm (#13148)
|
8 ماه پیش |
 Jared Van Bortel
|
2f567611c0
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
|
8 ماه پیش |
|
Jared Van Bortel
|
7d2123484e
convert : use correct context length for nomic-embed-text-v2 (#13216)
|
8 ماه پیش |
|
Xuan-Son Nguyen
|
074e42ab31
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
|
8 ماه پیش |
|
Georgi Gerganov
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
8 ماه پیش |
 Sigbjørn Skjæret
|
cb06a3c363
llama : orion rope type is neox (#13261)
|
8 ماه پیش |
|
Sigbjørn Skjæret
|
626083faf7
llama : plamo rope type is neox (#13260)
|
8 ماه پیش |
 piDack
|
2af6880178
llama-chat : reset glmedge chat template (#13253)
|
8 ماه پیش |
 Shakil Ahmed
|
e84773ab60
mtmd-cli : fix out_of_range when input image path is empty (#13244)
|
8 ماه پیش |
|
Georgi Gerganov
|
fab647e884
server : add cache reuse card link to help (#13230)
|
8 ماه پیش |
|
Xuan-Son Nguyen
|
dcf886007d
convert : explicitly disable trust_remote_code for AutoConfig (#13246)
|
8 ماه پیش |
 bandoti
|
d24d592808
ci: fix cross-compile sync issues (#12804)
|
8 ماه پیش |
 Justin Santa Barbara
|
8efbdadc61
rpc : avoid uninitialized memory in serialize_tensor (#13210)
|
8 ماه پیش |
 Jesse Gross
|
f057808ffa
ggml: Don't assert fail when tensor data changes (#13222)
|
8 ماه پیش |
|
Diego Devesa
|
d7a14c42a1
build : fix build info on windows (#13239)
|
8 ماه پیش |
 Loïc Carrère
|
b6e4ff69b8
clip : (minicpmv) Re-enable upscaling of images smaller than the CLIP image size (#13237)
|
8 ماه پیش |
 matteo
|
e0f572c846
llama-chat : update GLM4 chat template (#13238)
|
8 ماه پیش |
|
Jeff Bolz
|
79f26e9e12
vulkan: Add bfloat16 support (#12554)
|
8 ماه پیش |
|
Jeff Bolz
|
fc727bcdd5
vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul shader (#13191)
|
8 ماه پیش |
|
Johannes Gäßler
|
b0ecbd434b
test: non-cont. b in test-backend-ops -o MUL_MAT (#13187)
|
8 ماه پیش |
