Aaron Teo
|
b05a9d650f
vendors: update miniaudio version (#16212)
|
3 months ago |
rtaluyev
|
27052978e4
readme : update bindings (#16144)
|
3 months ago |
Aman Gupta
|
077c94d0ca
CUDA: add a fused top-K MoE kernel (#16130)
|
3 months ago |
Daniel Bevenius
|
aa3ee0eb0b
model-conversion : add embedding prompt file support (#15871)
|
3 months ago |
Daniel Bevenius
|
d0991da39d
server : add support for external server for tests (#16243)
|
3 months ago |
junchao-zhao
|
aa719c2f88
ggml : fix loongarch lsx compilation error (#15864)
|
3 months ago |
Johannes Gäßler
|
4cdd0bb453
docs: fix typo [no ci] (#16244)
|
3 months ago |
Douglas Hanley
|
b5bd037832
llama : add support for qwen3 reranker (#15824)
|
3 months ago |
Georgi Gerganov
|
dfcd53f7ec
metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)
|
3 months ago |
Georgi Gerganov
|
4ea00794b8
metal : relax reorder conditions (#16216)
|
3 months ago |
Georgi Gerganov
|
02a6a82ae7
metal : restore im2col perf (#16219)
|
3 months ago |
Radoslav Gerganov
|
c498fc82fe
rpc : use ggml logging facilities
|
3 months ago |
Aaron Teo
|
e7a5130a20
codeowners: add ownership of zdnn backend [no ci] (#16232)
|
3 months ago |
Eve
|
bee378e098
ci: run the x64 and arm ci on the github machines instead (#16183)
|
3 months ago |
Aaron Teo
|
5fb557653b
devops: fix s390x docker release failure (#16231)
|
3 months ago |
Aaron Teo
|
4ae88d07d0
codeowners: add ownership of zdnn backend [no ci] (#16229)
|
3 months ago |
Johannes Gäßler
|
e789095502
llama: print memory breakdown on exit (#15860)
|
3 months ago |
Acly
|
f2a789e334
ggml : split graph allocations according to backend max buffer size (#15815)
|
3 months ago |
Tarek Dakhran
|
3a59971967
model : add label for LiquidAI LFM2-2.6B model (#16204)
|
3 months ago |
Jie Fu (傅杰)
|
63b54c81a6
model-conversion : make causal-verify-logits fails with model names containing "." (#16215)
|
3 months ago |
Uilian Ries
|
152729f884
common : add missing chrono header for common.cpp (#16211)
|
3 months ago |
Sigbjørn Skjæret
|
c0c59c1157
codeowners : match all requirements files (#16214)
|
3 months ago |
Jie Fu (傅杰)
|
7735706b93
model-conversion : run-org-model.py fails to run on mac m1 (#16213)
|
3 months ago |
Daniel Bevenius
|
4d9ea03d17
codeowners : use slash prefix for root files [no ci] (#16210)
|
3 months ago |
Jie Fu (傅杰)
|
8ba548dae2
model-conversion : fix the make targets in the README.md (#16209)
|
3 months ago |
Georgi Gerganov
|
f505bd83ca
ci : disable AMD workflows + update NVIDIA workflows (#16200)
|
3 months ago |
Georgi Gerganov
|
0889589dbe
ci : enable Vulkan workflow on Mac (#16194)
|
3 months ago |
Xiangyan Sun
|
4e29084ba4
ggml-cpu: Respect cpumask settings (#16164)
|
3 months ago |
Sigbjørn Skjæret
|
f6b4af3d04
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928)
|
3 months ago |
Aaron Teo
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
3 months ago |