 Jesse Gross
|
e4a091bafd
runner.go: Support resource usage command line options
|
8 months ago |
|
Jesse Gross
|
46a7c682f2
runner.go: Fix embeddings endpoint
|
8 months ago |
|
Jesse Gross
|
0b73cca386
runner.go: Fix resource leaks when removing sequences
|
9 months ago |
|
Jesse Gross
|
76718ead40
runner.go: Support MinP parameter
|
9 months ago |
|
Jesse Gross
|
477f529d26
runner.go: Implement RepeatLastN to penalize repeated tokens
|
9 months ago |
|
Jesse Gross
|
69cc5795a7
runner.go: Shift context window when KV cache space is exceeded
|
9 months ago |
|
Jesse Gross
|
523d84c563
llama.go: Use dynamic buffer for TokenToPiece
|
9 months ago |
|
Jesse Gross
|
ed19fad862
llama.go: Make batch memory allocation match configuration
|
9 months ago |
 jmorganca
|
a483a4c4ed
lint
|
9 months ago |
 Daniel Hiltgen
|
e9dd656ff5
Update sync with latest llama.cpp layout, and run against b3485
|
9 months ago |
|
Daniel Hiltgen
|
6c0d892498
Prefix all build artifacts with an OS/ARCH dir
|
11 months ago |
|
jmorganca
|
a29851bc9b
clean up metal code
|
11 months ago |
|
jmorganca
|
8dda9293fa
fix `Makefile` on windows
|
11 months ago |
|
jmorganca
|
b3c62dcafd
remove printing
|
11 months ago |
|
jmorganca
|
1da6c40f4f
lint
|
11 months ago |
|
jmorganca
|
dded27dcfa
fix metal
|
11 months ago |
|
jmorganca
|
24a741424f
fix build on windows
|
11 months ago |
|
jmorganca
|
083a9e9b4e
link metal
|
11 months ago |
|
jmorganca
|
d0703eaf44
wip
|
11 months ago |
|
jmorganca
|
ce00e387c3
wip meta
|
11 months ago |
|
jmorganca
|
763d7b601c
sync
|
11 months ago |
|
jmorganca
|
4d0e6c55b0
remove perl docs
|
11 months ago |
|
jmorganca
|
3375b82c56
remove build scripts
|
11 months ago |
|
jmorganca
|
a632a04426
fix output
|
11 months ago |
|
jmorganca
|
110f37ffb0
arch build
|
11 months ago |
|
jmorganca
|
f2f03ff7f2
add temporary makefile
|
11 months ago |
|
jmorganca
|
9966a055e5
fix cgo flags for darwin amd64
|
11 months ago |
|
jmorganca
|
43efc893d7
basic progress
|
1 year ago |
|
jmorganca
|
20afaae020
add more runner params
|
1 year ago |
|
jmorganca
|
b2ef3bf490
embeddings
|
1 year ago |
