Paul Tsochantaris
|
d2f650cb5b
metal : free metal objects (#5161)
|
1 rok pred |
Georgi Gerganov
|
35dec26cc2
sync : ggml
|
2 rokov pred |
Georgi Gerganov
|
d460510c72
ggml : minor type fix (int64_t -> size_t)
|
2 rokov pred |
0cc4m
|
2307523d32
ggml : add Vulkan backend (#2059)
|
2 rokov pred |
Abhilash Majumder
|
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
|
2 rokov pred |
Georgi Gerganov
|
b764b8f1d0
flake.lock: Update (#5162)
|
2 rokov pred |
Johannes Gäßler
|
9241c3a2ac
Apply min_p to unsorted tokens (#5115)
|
2 rokov pred |
Johannes Gäßler
|
b2b2bf988c
Tests for min_p, sampling queue (#5147)
|
2 rokov pred |
Marcus Dunn
|
af4980bfed
readme : add link to rust bindings (#5148)
|
2 rokov pred |
sharpHL
|
f2e69d28c0
llama : add support for Orion-14B (#5118)
|
2 rokov pred |
Kyle Mistele
|
39baaf55a1
docker : add server-first container images (#5157)
|
2 rokov pred |
John
|
6db2b41a76
llava : support for Yi-VL and fix for mobileVLM (#5093)
|
2 rokov pred |
Georgi Gerganov
|
753eafed0e
sync : ggml
|
2 rokov pred |
Judd
|
e976423005
ggml : check ggml_add src1 type (ggml/708)
|
2 rokov pred |
Michael Klimenko
|
35a2ee9143
Remove unused data and add fixes (#5154)
|
2 rokov pred |
Maximilian Winter
|
ec903c0341
server : add self-extend support (#5104)
|
2 rokov pred |
0cc4m
|
a1d6df129b
Add OpenCL add kernel (#5151)
|
2 rokov pred |
Jared Van Bortel
|
bbe7c56c99
cmake : pass CPU architecture flags to nvcc (#5146)
|
2 rokov pred |
slaren
|
62fead3ea0
cuda : fix tensor size calculation for non-split buffer (#5145)
|
2 rokov pred |
slaren
|
15b4538ff2
ggml-alloc : add 10% margin to the buffer sizes (#5149)
|
2 rokov pred |
snadampal
|
7032f4f634
ggml : update softmax n_task calculation (#5126)
|
2 rokov pred |
Georgi Gerganov
|
5f1925a8ce
scripts : move run-with-preset.py from root to scripts folder
|
2 rokov pred |
Georgi Gerganov
|
3b7c914de2
tests : gitignore test-c.o
|
2 rokov pred |
Xuan Son Nguyen
|
48c857aa10
server : refactored the task processing logic (#5065)
|
2 rokov pred |
crasm
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
2 rokov pred |
Paul Tsochantaris
|
6dd3c28c9c
metal : remove unused `n_buffers` and `buffers` (#5129)
|
2 rokov pred |
Riceball LEE
|
38b431de23
gguf : fix "general.alignment" type in gguf_reader.py (#5136)
|
2 rokov pred |
Georgi Gerganov
|
aad0b01d73
readme : update hot topics
|
2 rokov pred |
Kawrakow
|
1182cf4d4f
Another bucket sort (#5109)
|
2 rokov pred |
XiaotaoChen
|
fe54033b69
readme : add MobileVLM 1.7B/3B to the supported models list (#5107)
|
2 rokov pred |