 AidanBeltonS
|
6bf9b66fa3
[SYCL] Update SYCL upscale operation (#7321)
|
1 سال پیش |
 Bingan
|
26cd4237bc
Update README.md (#7410)
|
1 سال پیش |
 Herman Semenov
|
213e90ed73
ggml-opencl, llama: using reserve() if count already known (#7272)
|
1 سال پیش |
 junchao-loongson
|
65c58207ec
ggml : add loongarch lsx and lasx support (#6454)
|
1 سال پیش |
 Georgi Gerganov
|
1cc0155d04
server : tuning tests (#7388)
|
1 سال پیش |
|
Georgi Gerganov
|
e932094d58
server : return error on too large embedding input (#7389)
|
1 سال پیش |
|
Georgi Gerganov
|
2789baf480
tests : fix --keep_split -> --keep-split (#7374)
|
1 سال پیش |
 Srihari-mcw
|
33c8d50acc
Add provisions for windows support for BF16 code including CMake provision for enabling AVX512_BF16 (#7258)
|
1 سال پیش |
 slaren
|
d359f30921
llama : remove MPI backend (#7395)
|
1 سال پیش |
 Fred Douglas
|
1ea2a0036e
quantize : fix --keep-split check (#7374)
|
1 سال پیش |
 0cc4m
|
f030ec1f7a
Vulkan Embedding Fix (#7360)
|
1 سال پیش |
|
slaren
|
e4e6f67be6
ggml : fix another case of quants nans (#7387)
|
1 سال پیش |
 Johannes Gäßler
|
5ca49cbecd
ggml: implement quantized KV cache for FA (#7372)
|
1 سال پیش |
|
Johannes Gäßler
|
1b01f06db0
server: add test for token probs (#7347)
|
1 سال پیش |
|
Johannes Gäßler
|
41858392e1
server: fix seed being reported back (#7382)
|
1 سال پیش |
 Anas Ahouzi
|
6aade19ee7
Add StableLM2 pre-tokenizer (#7349)
|
1 سال پیش |
|
slaren
|
ab33f7a338
cuda : clear error after buffer allocation failure (#7376)
|
1 سال پیش |
 Brian
|
e23b974f4c
labeler.yml: Use settings from ggerganov/llama.cpp [no ci] (#7363)
|
1 سال پیش |
|
Georgi Gerganov
|
854d365aba
cmake : update android comments (#7341)
|
1 سال پیش |
 fraxy-v
|
f5bf761747
Capture CUDA logging output (#7298)
|
1 سال پیش |
|
Georgi Gerganov
|
059031b8c4
ci : re-enable sanitizer runs (#7358)
|
1 سال پیش |
|
Georgi Gerganov
|
511182eabb
android : use "ci-android" branch for CI (#7341)
|
1 سال پیش |
|
Johannes Gäßler
|
133d99c599
CUDA: deduplicate FlashAttention code (#7352)
|
1 سال پیش |
|
Johannes Gäßler
|
cb42c29427
server: correct --threads documentation [no ci] (#7362)
|
1 سال پیش |
 Engininja2
|
d233b507cd
cuda : add half2 __shfl_xor() for ROCm 5.5 (#7263)
|
1 سال پیش |
 Steffen Röcker
|
0f98acfac6
llama : add support for larger Granite Code Models (20B, 34B) (#7324)
|
1 سال پیش |
 strawberrymelonpanda
|
ca57e0f35e
perplexity : ndot progress and show stats with < 100 tasks (#7348)
|
1 سال پیش |
|
0cc4m
|
c1b295eea5
Update and fix Vulkan soft_max and argsort implementations (#7237)
|
1 سال پیش |
|
Brian
|
de73196344
github-actions-labeler: initial commit (#7330)
|
1 سال پیش |
|
Georgi Gerganov
|
b49a13dd2f
convert : fix set_vocab_sentencepiece (#6866)
|
1 سال پیش |
