 Kawrakow
|
8e14e3ddb3
Faster AVX2 dot product for IQ2_XS (#5187)
|
2 سال پیش |
|
Kawrakow
|
f4d7e54974
SOTA 3-bit quants (#5196)
|
2 سال پیش |
 0cc4m
|
2256f36b79
Vulkan Windows APU Memory Handling (#5199)
|
2 سال پیش |
 Vladimir Malyutin
|
7359016c7c
quantize : fix typo (#5211)
|
2 سال پیش |
 divinity76
|
813416991a
main : allow empty --prompt-cache file (#5176)
|
2 سال پیش |
 Romain Neutron
|
5589921ef8
readme : minor (#5204)
|
2 سال پیش |
 Georgi Gerganov
|
49f44b5c55
readme : update hot topics
|
2 سال پیش |
 Wu Jian Ping
|
6685cc41c2
server : improve README (#5209)
|
2 سال پیش |
 Paul Tsochantaris
|
ceebbb5b21
ggml alloc: Fix for null dereference on alloc failure (#5200)
|
2 سال پیش |
 Jared Van Bortel
|
6daa69ee81
kompute : fix fallback to CPU (#5201)
|
2 سال پیش |
|
Jared Van Bortel
|
fbf1ddec69
Nomic Vulkan backend (#4456)
|
2 سال پیش |
|
divinity76
|
2aed77eb06
fix typo "RLIMIT_MLOCK" (#5175)
|
2 سال پیش |
 Wu Jian Ping
|
c82d18e863
server : embeddings compatibility for OpenAI (#5190)
|
2 سال پیش |
|
Georgi Gerganov
|
14fef85e2d
py : fix except (#5194)
|
2 سال پیش |
 Sang-Kil Park
|
e76627bcce
py : improve BPE tokenizer support (#5189)
|
2 سال پیش |
 slaren
|
fbe7dfa53c
ggml : add max buffer sizes to opencl and metal backends (#5181)
|
2 سال پیش |
 Eve
|
172ac82629
cmake : fix Vulkan build (#5182)
|
2 سال پیش |
|
Paul Tsochantaris
|
d2f650cb5b
metal : free metal objects (#5161)
|
2 سال پیش |
|
Georgi Gerganov
|
35dec26cc2
sync : ggml
|
2 سال پیش |
|
Georgi Gerganov
|
d460510c72
ggml : minor type fix (int64_t -> size_t)
|
2 سال پیش |
|
0cc4m
|
2307523d32
ggml : add Vulkan backend (#2059)
|
2 سال پیش |
 Abhilash Majumder
|
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
|
2 سال پیش |
|
Georgi Gerganov
|
b764b8f1d0
flake.lock: Update (#5162)
|
2 سال پیش |
 Johannes Gäßler
|
9241c3a2ac
Apply min_p to unsorted tokens (#5115)
|
2 سال پیش |
|
Johannes Gäßler
|
b2b2bf988c
Tests for min_p, sampling queue (#5147)
|
2 سال پیش |
 Marcus Dunn
|
af4980bfed
readme : add link to rust bindings (#5148)
|
2 سال پیش |
 sharpHL
|
f2e69d28c0
llama : add support for Orion-14B (#5118)
|
2 سال پیش |
 Kyle Mistele
|
39baaf55a1
docker : add server-first container images (#5157)
|
2 سال پیش |
 John
|
6db2b41a76
llava : support for Yi-VL and fix for mobileVLM (#5093)
|
2 سال پیش |
|
Georgi Gerganov
|
753eafed0e
sync : ggml
|
2 سال پیش |
