 slaren
|
8cb508d0d5
disable publishing the full-rocm docker image (#8083)
|
1 year ago |
 Yann Follet
|
646ef4a9cf
embedding : more cli arguments (#7458)
|
1 year ago |
 fairydreaming
|
de0d6a68ac
gguf-py, convert-hf : model conversion support for T5 and FLAN-T5 model variants (#5763)
|
1 year ago |
|
slaren
|
95f57bb5d5
ggml : remove ggml_task_type and GGML_PERF (#8017)
|
1 year ago |
 Eddie-Wang
|
e112b610a1
llama : add support for BitnetForCausalLM (#7931)
|
1 year ago |
 Aarni Koskela
|
6a2f298bd7
server : fix JSON-Scheme typo (#7975)
|
1 year ago |
 Daniel Bevenius
|
11318d9aa1
Fix typo in llama_set_embeddings comment (#8077)
|
1 year ago |
|
slaren
|
b6b9a8e606
fix CI failures (#8066)
|
1 year ago |
 0cc4m
|
45c0e2e4c1
Refactor Vulkan backend to allow multiple contexts (#7961)
|
1 year ago |
 Clint Herron
|
b5a5f34efa
Removing extra blank lines that were breaking Lint. (#8067)
|
1 year ago |
 Xuan Son Nguyen
|
3e58b0ee35
cvector: fix CI + correct help message (#8064)
|
1 year ago |
 HatsuneMikuUwU33
|
adf480c3ab
cvector-generator: Moe Moe Fixie-Fixie for Lots of Formats~! ♡(ᐢ ᴥ ᐢ)♡ (#8052)
|
1 year ago |
 0xspringtime
|
3aa184a8c7
convert-hf : change assert to exception (#8015)
|
1 year ago |
 ddh0
|
5b48cd53a8
Update llama-quantize ppl/file size output from LLaMA-v1 to Llama-3 values (#8058)
|
1 year ago |
|
Clint Herron
|
c5a8d4b749
JSON Schema to GBNF integration tests (#7790)
|
1 year ago |
 k.h.lai
|
557b653dc9
vulkan: detect multiple devices by deviceUUID instead of deviceID (#8022)
|
1 year ago |
 Eve
|
7d5e8777ae
ggml : AVX IQ quants (#7845)
|
1 year ago |
 Georgi Gerganov
|
a927b0f3dd
llama : optimize long word tokenization with WPM (#8034)
|
1 year ago |
 Douglas Hanley
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
1 year ago |
 Shuichi Tsutsumi
|
0e64591e82
swiftui : enable stream updating (#7754)
|
1 year ago |
 Hamdoud Hakem
|
b1ef562bc1
requirements : Bump torch and numpy for python3.12 (#8041)
|
1 year ago |
|
Hamdoud Hakem
|
17b291a6a5
convert-hf : Fix the encoding in the convert-hf-to-gguf-update.py (#8040)
|
1 year ago |
 Johannes Gäßler
|
abd894ad96
common: fix warning (#8036)
|
1 year ago |
 luoyu-intel
|
de391e4c80
[SYCL] Fix windows build and inference (#8003)
|
1 year ago |
|
Johannes Gäßler
|
d50f8897a7
CUDA: stream-k decomposition for MMQ (#8018)
|
1 year ago |
 Michael de Gans
|
2075a66a96
metal : fix `ggml_metal_supports_op` for BF16 (#8021)
|
1 year ago |
 sasha0552
|
ba58993152
server : fix smart slot selection (#8020)
|
1 year ago |
|
Michael de Gans
|
a7854743c5
un-ignore `build-info.cmake` and `build-info.sh` (#7996)
|
1 year ago |
|
slaren
|
9c77ec1d74
ggml : synchronize threads using barriers (#7993)
|
1 year ago |
|
Georgi Gerganov
|
a04a953cab
codecov : remove (#8004)
|
1 year ago |
