| .. |
|
ext_server
|
80c1a3f812
playing around with truncate stuff
|
10 kuukautta sitten |
|
generate
|
b0930626c5
Add back lower level parallel flags
|
11 kuukautta sitten |
|
llama.cpp @ 7c26775adb
|
152fc202f5
llm: update llama.cpp commit to `7c26775` (#4896)
|
11 kuukautta sitten |
|
patches
|
152fc202f5
llm: update llama.cpp commit to `7c26775` (#4896)
|
11 kuukautta sitten |
|
filetype.go
|
d6f692ad1a
Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)
|
1 vuosi sitten |
|
ggla.go
|
171eb040fc
simplify safetensors reading
|
1 vuosi sitten |
|
ggml.go
|
6fd04ca922
Improve multi-gpu handling at the limit
|
11 kuukautta sitten |
|
gguf.go
|
7bdcd1da94
Revert "Merge pull request #4938 from ollama/mxyng/fix-byte-order"
|
11 kuukautta sitten |
|
llm.go
|
829ff87bd1
revert tokenize ffi (#4761)
|
11 kuukautta sitten |
|
llm_darwin_amd64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 vuosi sitten |
|
llm_darwin_arm64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 vuosi sitten |
|
llm_linux.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 vuosi sitten |
|
llm_windows.go
|
058f6cd2cc
Move nested payloads to installer and zip file on windows
|
1 vuosi sitten |
|
memory.go
|
359b15a597
Handle models with divergent layer sizes
|
11 kuukautta sitten |
|
memory_test.go
|
6f351bf586
review comments and coverage
|
11 kuukautta sitten |
|
payload.go
|
6f351bf586
review comments and coverage
|
11 kuukautta sitten |
|
server.go
|
c111d8bb51
normalization
|
10 kuukautta sitten |
|
status.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 vuosi sitten |
Roy Han
80c1a3f812
playing around with truncate stuff