| .. |
|
ext_server
|
2cc854f8cb
llm: fix missing dylibs by restoring old build behavior on Linux and macOS (#5511)
|
10 bulan lalu |
|
generate
|
9ae146993e
llm: add `GGML_STATIC` flag to windows static lib
|
10 bulan lalu |
|
llama.cpp @ d7fd29fff1
|
8f8e736b13
update llama.cpp submodule to `d7fd29f` (#5475)
|
10 bulan lalu |
|
patches
|
8f8e736b13
update llama.cpp submodule to `d7fd29f` (#5475)
|
10 bulan lalu |
|
filetype.go
|
d6f692ad1a
Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)
|
1 tahun lalu |
|
ggla.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 bulan lalu |
|
ggml.go
|
de2163dafd
gemma2 graph
|
10 bulan lalu |
|
ggml_test.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 bulan lalu |
|
gguf.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 bulan lalu |
|
llm.go
|
5304b765b2
llm: put back old include dir (#5507)
|
10 bulan lalu |
|
llm_darwin_amd64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 tahun lalu |
|
llm_darwin_arm64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 tahun lalu |
|
llm_linux.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 tahun lalu |
|
llm_windows.go
|
058f6cd2cc
Move nested payloads to installer and zip file on windows
|
1 tahun lalu |
|
memory.go
|
8e0641a9bf
handle asymmetric embedding KVs
|
11 bulan lalu |
|
memory_test.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 bulan lalu |
|
payload.go
|
0e982bc1f4
Fix corner cases on tmp cleaner on mac
|
10 bulan lalu |
|
server.go
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
10 bulan lalu |
|
status.go
|
4d71c559b2
fix error detection by limiting model loading error parsing (#5472)
|
10 bulan lalu |
jmorganca
9ae146993e
llm: add `GGML_STATIC` flag to windows static lib