 Daniel Bevenius
|
dada4c846d
model-conversion : remove max diff check in compare-logits [no ci] (#17954)
|
hai 1 mes |
 Adrien Gallouët
|
b8ee22cfde
common : add minimalist multi-thread progress bar (#17602)
|
hai 1 mes |
 Gustavo Rocha Dias
|
2eaa2c65cb
cmake: link ws2_32 for MinGW/w64devkit builds in cpp-httplib (#17949)
|
hai 1 mes |
 yulo
|
c33a58bced
HIP: enable mmf for RDNA3 (#17879)
|
hai 1 mes |
 Pascal
|
a81a569577
Add a search field on model selector / improve mobile display (#17765)
|
hai 1 mes |
 Piotr Wilkin (ilintar)
|
53ecd4fdb9
SOLVE_TRI extension to more dimensions (#17793)
|
hai 1 mes |
 Georgi Gerganov
|
c6f6e4f96a
ggml-alloc : fix reuse-parent logic for misaligned sizes (#17884)
|
hai 1 mes |
|
Georgi Gerganov
|
d9f8f60618
batch : fix sequence id ownership (#17915)
|
hai 1 mes |
 Yuichiro Utsumi
|
e4ae383317
docs: use port 8080 in Docker examples (#17903)
|
hai 1 mes |
 nullname
|
34ce48d97a
ggml-hexagon: fix `rope` failure at `test-backend-ops` (#17565)
|
hai 1 mes |
 Sigbjørn Skjæret
|
45e350e3d3
ci: fix riscv64-native build (#17916)
|
hai 1 mes |
 Xuan-Son Nguyen
|
c6b2c9310c
mtmd: some small clean up (#17909)
|
hai 1 mes |
|
Xuan-Son Nguyen
|
34a6d86982
cli: enable jinja by default (#17911)
|
hai 1 mes |
|
Pascal
|
f32ca51bfe
server: add presets (config) when using multiple models (#17859)
|
hai 1 mes |
 Max Krasnyansky
|
e1f4921980
Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (#17748)
|
hai 1 mes |
|
Georgi Gerganov
|
4dff236a52
ggml : remove GGML_KQ_MASK_PAD constant (#17910)
|
hai 1 mes |
|
Sigbjørn Skjæret
|
4df6e859e9
cuda : add missing support check for xielu (#17895)
|
hai 1 mes |
|
Xuan-Son Nguyen
|
6c2131773c
cli: new CLI experience (#17824)
|
hai 1 mes |
 Eric Zhang
|
b677721819
model : Qwen3-Next-80B-A3B has 48 layers (#17898)
|
hai 1 mes |
 lhez
|
2d2e1030e3
docs : update opencl ops (#17904)
|
hai 1 mes |
 Johannes Gäßler
|
17f7f4baad
CUDA: fix unpadded strides in MMA FA kernel (#17891)
|
hai 1 mes |
|
Xuan-Son Nguyen
|
9e79b0116e
convert: allow using quantized Mistral weight (#17889)
|
hai 1 mes |
 Neo Zhang Jianyu
|
2e9eab80c2
fix softmax for iGPU (#17838)
|
hai 1 mes |
 Aldehir Rojas
|
2fbe3b7bb7
common : add parser for ministral/mistral large 3/devstral 2 (#17713)
|
hai 1 mes |
|
Sigbjørn Skjæret
|
63391852b0
docs : update cpu and cuda ops (#17890)
|
hai 1 mes |
 Gabe Goodhart
|
086a63e3a5
metal: SSM kernel improvements (#17876)
|
hai 1 mes |
|
Piotr Wilkin (ilintar)
|
b63509262a
Add DIAG for CUDA (#17873)
|
hai 1 mes |
|
Johannes Gäßler
|
48f47565a7
docs: clarify that CPU support should be first (#17886)
|
hai 1 mes |
|
Gabe Goodhart
|
02e409a5be
ggml : Provide macos-specific backtrace printing to avoid terminal death (#17869)
|
hai 1 mes |
|
Georgi Gerganov
|
6b82eb7883
metal : print node names for debugging (#17882)
|
hai 1 mes |
