Johannes Gäßler
|
4cdd0bb453
docs: fix typo [no ci] (#16244)
|
3 месяцев назад |
Douglas Hanley
|
b5bd037832
llama : add support for qwen3 reranker (#15824)
|
3 месяцев назад |
Georgi Gerganov
|
dfcd53f7ec
metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)
|
3 месяцев назад |
Georgi Gerganov
|
4ea00794b8
metal : relax reorder conditions (#16216)
|
3 месяцев назад |
Georgi Gerganov
|
02a6a82ae7
metal : restore im2col perf (#16219)
|
3 месяцев назад |
Radoslav Gerganov
|
c498fc82fe
rpc : use ggml logging facilities
|
3 месяцев назад |
Aaron Teo
|
e7a5130a20
codeowners: add ownership of zdnn backend [no ci] (#16232)
|
3 месяцев назад |
Eve
|
bee378e098
ci: run the x64 and arm ci on the github machines instead (#16183)
|
3 месяцев назад |
Aaron Teo
|
5fb557653b
devops: fix s390x docker release failure (#16231)
|
3 месяцев назад |
Aaron Teo
|
4ae88d07d0
codeowners: add ownership of zdnn backend [no ci] (#16229)
|
3 месяцев назад |
Johannes Gäßler
|
e789095502
llama: print memory breakdown on exit (#15860)
|
3 месяцев назад |
Acly
|
f2a789e334
ggml : split graph allocations according to backend max buffer size (#15815)
|
3 месяцев назад |
Tarek Dakhran
|
3a59971967
model : add label for LiquidAI LFM2-2.6B model (#16204)
|
3 месяцев назад |
Jie Fu (傅杰)
|
63b54c81a6
model-conversion : make causal-verify-logits fails with model names containing "." (#16215)
|
3 месяцев назад |
Uilian Ries
|
152729f884
common : add missing chrono header for common.cpp (#16211)
|
3 месяцев назад |
Sigbjørn Skjæret
|
c0c59c1157
codeowners : match all requirements files (#16214)
|
3 месяцев назад |
Jie Fu (傅杰)
|
7735706b93
model-conversion : run-org-model.py fails to run on mac m1 (#16213)
|
3 месяцев назад |
Daniel Bevenius
|
4d9ea03d17
codeowners : use slash prefix for root files [no ci] (#16210)
|
3 месяцев назад |
Jie Fu (傅杰)
|
8ba548dae2
model-conversion : fix the make targets in the README.md (#16209)
|
3 месяцев назад |
Georgi Gerganov
|
f505bd83ca
ci : disable AMD workflows + update NVIDIA workflows (#16200)
|
3 месяцев назад |
Georgi Gerganov
|
0889589dbe
ci : enable Vulkan workflow on Mac (#16194)
|
3 месяцев назад |
Xiangyan Sun
|
4e29084ba4
ggml-cpu: Respect cpumask settings (#16164)
|
3 месяцев назад |
Sigbjørn Skjæret
|
f6b4af3d04
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928)
|
3 месяцев назад |
Aaron Teo
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
3 месяцев назад |
Daniel Bevenius
|
0bc7cc7154
codeowners : add @danbev to model-conversion example [no ci] (#16190)
|
3 месяцев назад |
Aaron Teo
|
4b9f4cb0f8
devops: add s390x containers (#15915)
|
3 месяцев назад |
Daniel Bevenius
|
85e72271ba
ggml-cpu : fix typo in gemm comments [no ci] (#16189)
|
3 месяцев назад |
Gabe Goodhart
|
1d0125bcf1
feat: Add conversion support in GraniteHybrid for non-hybrid (all attn) (#16177)
|
3 месяцев назад |
Haiyue Wang
|
351f3da39c
clang-tidy : disable warning about performance enum size (#16127)
|
3 месяцев назад |
Sigbjørn Skjæret
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
3 месяцев назад |