 Xuan-Son Nguyen
|
3c3635d2f2
server : speed up tests (#15836)
|
4 months ago |
|
Xuan-Son Nguyen
|
61bdfd5298
server : implement prompt processing progress report in stream mode (#15827)
|
4 months ago |
 Johannes Gäßler
|
01806e7771
ggml-cpu: document use of "free" memory [no ci] (#15834)
|
4 months ago |
 Aaron Teo
|
186415d595
ggml-cpu: drop support for nnpa intrinsics (#15821)
|
4 months ago |
 Gabe Goodhart
|
fd621880f3
aLoRA Support (#15327)
|
4 months ago |
 Sigbjørn Skjæret
|
4281c7b315
ci : exempt correct research label (#15825)
|
4 months ago |
|
Gabe Goodhart
|
5fac79cbc7
Thinking model disabled assistant prefill (#15404)
|
4 months ago |
 Eric Curtin
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
4 months ago |
|
Johannes Gäßler
|
5143fa895e
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (#15802)
|
4 months ago |
 Daniel Bevenius
|
3a550b5ca4
tests : add --list-ops and --show-coverage options (#15745)
|
4 months ago |
 Erik Scholz
|
a81283820a
gguf: gguf_writer refactor (#15691)
|
4 months ago |
 Georgi Gerganov
|
c610b6c11b
kv-cache : fix SWA checks + disable cacheless iSWA (#15811)
|
4 months ago |
|
Daniel Bevenius
|
5d6688de08
model-conversion : add --embeddings flag to modelcard.template [no ci] (#15801)
|
4 months ago |
 ExtReMLapin
|
4fd1242bef
chat : fixed crash when Hermes 2 <tool_call> had a newline before it (#15639)
|
4 months ago |
 Piotr Wilkin (ilintar)
|
b2426e469e
chat : nemotron thinking & toolcalling support (#15676)
|
4 months ago |
|
Piotr Wilkin (ilintar)
|
9e2b1e83c6
scripts : add Jinja tester PySide6 simple app (#15756)
|
4 months ago |
|
Daniel Bevenius
|
fb15d649ed
llama : add support for EmbeddingGemma 300m (#15798)
|
4 months ago |
|
Gabe Goodhart
|
856ed0947f
metal : Add template specialization for mul_mm_id w/ ne20 == 10 (#15799)
|
4 months ago |
|
Daniel Bevenius
|
d1e2adba65
llama : set n_outputs to 1 to avoid 0 outputs mean-pooling (#15791)
|
4 months ago |
 Chenguang Li
|
c1c354e44c
CANN: Refactor ND to NZ workspace to be per-device (#15763)
|
4 months ago |
|
Xuan-Son Nguyen
|
a68d914426
server: add exceed_context_size_error type (#15780)
|
4 months ago |
 Eric Curtin
|
badb80cadb
Document the new max GPU layers default in help (#15771)
|
4 months ago |
 leejet
|
0a1b3982cd
ggml: add ops for WAN video model (cuda && cpu) (#15669)
|
4 months ago |
 hipudding
|
5421f63ab0
CANN: Fix precision issue on 310I DUO multi-devices (#15784)
|
4 months ago |
 rmatif
|
820bc98531
opencl: add hs=40 to FA (#15758)
|
4 months ago |
|
Chenguang Li
|
239b60e898
CANN: fix acl_rstd allocation size in ggml_cann_rms_norm (#15760)
|
4 months ago |
 Ruben Ortlam
|
dff7551bfd
vulkan: fix mmv subgroup16 selection (#15775)
|
4 months ago |
 Jeff Bolz
|
0fce7a1248
vulkan: don't use std::string in load_shaders, to improve compile time (#15724)
|
4 months ago |
|
Daniel Bevenius
|
8227695d7a
vulkan : update ggml_vk_instance_validation_ext_available (#15666)
|
4 months ago |
 Shin-myoung-serp
|
0014fb4add
ggml vulkan: add hardsigmoid and hardswish operations (#15762)
|
4 months ago |
