 0cc4m
|
3d7ebf6312
Vulkan Mixture of Experts (MoE) support (#7628)
|
1 year ago |
 Andy Tai
|
a10cda58d3
cmake : add pkg-config spec file for llama.cpp (#7702)
|
1 year ago |
 zhangkaihuo
|
6f28a333c1
llama : MiniCPM support tied embeddings (#7664)
|
1 year ago |
 Georgi Gerganov
|
549279d804
llama : avoid double token-to-piece cache (#7654)
|
1 year ago |
 woachk
|
9e405b6e2e
kompute : implement op_getrows_f32 (#6403)
|
1 year ago |
 Dave Airlie
|
3413ae2193
fix bug introduced in using calloc (#7701)
|
1 year ago |
|
Georgi Gerganov
|
1669810d7c
flake.lock: Update (#7686)
|
1 year ago |
 Austin
|
7c4e5b7eae
chore : add ignore rule for generated server themes (#7689)
|
1 year ago |
 nickp27
|
9422c5e34b
[SYCL] Update rpc-server.cpp to include SYCL backend (#7682)
|
1 year ago |
 Johannes Gäßler
|
e141ce624a
Fix FlashAttention debug test, FP32 assert (#7684)
|
1 year ago |
 Yazan Agha-Schrader
|
2e666832e6
server : new UI (#7633)
|
1 year ago |
 HanishKVC
|
2ac95c9d56
SimpleChat: Simple histogram/repeatMatching driven garbageTrimming, Settings UI, Streaming mode, OpenAi Compat (Model, Authorization Bearer), Save/Restore session, Auto Settings UI (#7548)
|
1 year ago |
|
Johannes Gäßler
|
750f60c03e
CUDA: fix Pascal FA, deq. KV to FP16 for batch > 8 (#7681)
|
1 year ago |
|
Johannes Gäßler
|
9b596417af
CUDA: quantized KV support for FA vec (#7527)
|
1 year ago |
|
Georgi Gerganov
|
a323ec60af
server : update js (#7670)
|
1 year ago |
 Galunid
|
0515ad93f4
convert-hf : Handle NotImplementedError in convert-hf-to-gguf (#7660)
|
1 year ago |
|
Johannes Gäßler
|
c8047d538f
scripts: update compare_llama_bench.py [no ci] (#7673)
|
1 year ago |
 Daniele
|
30e238b246
Improve HIP compatibility (#7672)
|
1 year ago |
|
Georgi Gerganov
|
16926dff92
readme : link homebrew discussion
|
1 year ago |
|
Georgi Gerganov
|
0c27e6f62e
ggml : fix loongson compile warnings (#7537)
|
1 year ago |
|
Galunid
|
2e32f874e6
Somehow '**' got lost (#7663)
|
1 year ago |
|
Galunid
|
1af511fc22
Add convert.py removal to hot topics (#7662)
|
1 year ago |
 Sertaç Özercan
|
0541f06296
[no ci] docs: add aikit to readme (#7650)
|
1 year ago |
 JohnnyB
|
9022c33646
Fixed painfully slow single process builds. (#7326)
|
1 year ago |
|
Georgi Gerganov
|
5921b8f089
llama : cache llama_token_to_piece (#7587)
|
1 year ago |
 Martin Delille
|
5dcdf94676
Fix conan badge display [no ci] (#7645)
|
1 year ago |
 Manuel
|
2e2340de17
Add brew installation instruction to README [no ci] (#7616)
|
1 year ago |
|
Martin Delille
|
7846540bd2
readme : add Conan badge (#7638)
|
1 year ago |
 Brian
|
e6157f94c8
github: add contact links to issues and convert question into research [no ci] (#7612)
|
1 year ago |
|
Galunid
|
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py (#7430)
|
1 year ago |
