 Michał Moskal
|
89daa2564f
llguidance build fixes for Windows (#11664)
|
11 miesięcy temu |
 lhez
|
300907b211
opencl: Fix rope and softmax (#11833)
|
11 miesięcy temu |
 Diego Devesa
|
94b87f87b5
cuda : add ampere to the list of default architectures (#11870)
|
11 miesięcy temu |
 Georgi Gerganov
|
dbc2ec59b5
docker : drop to CUDA 12.4 (#11869)
|
11 miesięcy temu |
 Daniel Bevenius
|
3d68f034da
llama : add completion for --chat-template-file (#11860)
|
11 miesięcy temu |
 Jinyang He
|
38e32eb6a0
ggml: optimize some vec dot functions for LoongArch ASX (#11842)
|
11 miesięcy temu |
 Eve
|
a4f011e8d0
vulkan: linux builds + small subgroup size fixes (#11767)
|
11 miesięcy temu |
 theraininsky
|
a7b8ce2260
llama-bench : fix unexpected global variable initialize sequence issue (#11832)
|
11 miesięcy temu |
|
Georgi Gerganov
|
04045bb842
readme : minor
|
11 miesięcy temu |
 Jeffrey Morgan
|
8a8c4ceb60
llamafile: use member variable instead of constant for iq4nlt (#11780)
|
11 miesięcy temu |
 Reza Rahemtola
|
c1f958c038
server : (docs) Update wrong tool calling example (#11809)
|
11 miesięcy temu |
|
Daniel Bevenius
|
c48f630d1c
llama : add --completion-bash option (#11846)
|
11 miesięcy temu |
 R0CKSTAR
|
bd6e55bfd3
musa: bump MUSA SDK version to rc3.1.1 (#11822)
|
11 miesięcy temu |
 Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 miesięcy temu |
 Vinesh Janarthanan
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
11 miesięcy temu |
 Oleksandr Kuvshynov
|
e4376270d9
llama.cpp: fix warning message (#11839)
|
11 miesięcy temu |
|
Daniel Bevenius
|
3e69319772
llama : update llama_decode_internal ref [no ci] (#11840)
|
11 miesięcy temu |
|
Diego Devesa
|
a394039db0
ggml-cpu : add chunking support to mul_mat_id (#11666)
|
11 miesięcy temu |
 Xuan-Son Nguyen
|
be3bbd6215
ggml : x2 speed for WASM by optimizing SIMD (#11453)
|
11 miesięcy temu |
 Woof Dog
|
31afcbee0e
server : (webui) Give copy button back to all message bubbles (#11814)
|
11 miesięcy temu |
 uvos
|
5c4284d57b
HIP: Remove GCN from list of devices that avoid MMQ (#11831)
|
11 miesięcy temu |
 JC
|
bfd11a2344
Fix: Compile failure due to Microsoft STL breaking change (#11836)
|
11 miesięcy temu |
|
Georgi Gerganov
|
0fb77f821f
sync : ggml
|
11 miesięcy temu |
|
uvos
|
e598697d63
HIP: Switch to std::vector in rocblas version check (#11820)
|
11 miesięcy temu |
 bandoti
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
11 miesięcy temu |
 Richard
|
748ee9fe93
ggml : fix multi-threaded clamp_f32 (#11824)
|
11 miesięcy temu |
 Weizhao Ouyang
|
198b1ec611
ggml-cpu: Fix duplicate MATMUL_INT8 (#11817)
|
11 miesięcy temu |
 Johannes Gäßler
|
c3d6af7cd2
CUDA: fix CUDART_VERSION checks (#11821)
|
11 miesięcy temu |
|
Daniel Bevenius
|
369be5598a
llama : fix typo in llama-grammar.h [no ci] (#11816)
|
11 miesięcy temu |
|
lhez
|
4078c77f98
docs: add OpenCL (#11697)
|
11 miesięcy temu |
