| .. |
|
ext_server
|
90ca84172c
Fix embeddings memory corruption (#6467)
|
vor 8 Monaten |
|
generate
|
0b03b9c32f
llm: Align cmake define for cuda no peer copy (#6455)
|
vor 8 Monaten |
|
llama.cpp @ 1e6f6554aa
|
e04c7012c2
update llama.cpp submodule to `1e6f6554` (#6208)
|
vor 8 Monaten |
|
patches
|
90ca84172c
Fix embeddings memory corruption (#6467)
|
vor 8 Monaten |
|
filetype.go
|
d6f692ad1a
Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)
|
vor 11 Monaten |
|
ggla.go
|
6b252918fb
update convert test to check result data
|
vor 9 Monaten |
|
ggml.go
|
0c819e167b
convert safetensor adapters into GGUF (#6327)
|
vor 8 Monaten |
|
ggml_test.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
vor 10 Monaten |
|
gguf.go
|
0e1ec461f9
import
|
vor 8 Monaten |
|
llm.go
|
b732beba6a
lint
|
vor 9 Monaten |
|
llm_darwin_amd64.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
vor 9 Monaten |
|
llm_darwin_arm64.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
vor 9 Monaten |
|
llm_linux.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
vor 9 Monaten |
|
llm_windows.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
vor 9 Monaten |
|
memory.go
|
8e0641a9bf
handle asymmetric embedding KVs
|
vor 10 Monaten |
|
memory_test.go
|
01b20fe6f1
lint
|
vor 8 Monaten |
|
payload.go
|
d470ebe78b
Add Jetson cuda variants for arm
|
vor 8 Monaten |
|
server.go
|
397cae7962
llm: fix typo in comment (#6530)
|
vor 8 Monaten |
|
status.go
|
04210aa6dd
Catch one more error log
|
vor 9 Monaten |
Josh Yan
0e1ec461f9
import