 Alex Cheema
|
142682645f
bump up tinygrad version
|
1 year ago |
 Alex Cheema
|
044d189ccc
Merge pull request #94 from mzbac/mlx_refactor
|
1 year ago |
|
Alex Cheema
|
909d5ef8ba
Merge branch 'main' into mlx_refactor
|
1 year ago |
|
Alex Cheema
|
63e51a8270
formatting
|
1 year ago |
|
Alex Cheema
|
6695b019a2
format format.py
|
1 year ago |
|
Alex Cheema
|
1dc08fecaa
increase max line length to 200
|
1 year ago |
|
Alex Cheema
|
444137776a
formatting
|
1 year ago |
 Anchen
|
a6bb8ddf41
update deepseek sanitize to shard layers first before handle switch
|
1 year ago |
|
Alex Cheema
|
cb217b7b77
format format.py
|
1 year ago |
|
Alex Cheema
|
4cb36a7f55
increase max line length to 200
|
1 year ago |
|
Alex Cheema
|
d94e3f9ce4
formatting
|
1 year ago |
|
Anchen
|
666b1c83ee
refactor(mlx): model sharding and add deepseek v2 support
|
1 year ago |
|
Alex Cheema
|
931ced7c01
fix a few more linter errors
|
1 year ago |
|
Alex Cheema
|
57b2f2a4e2
fix ruff lint errors
|
1 year ago |
|
Alex Cheema
|
ce761038ac
formatting / linting
|
1 year ago |
|
Alex Cheema
|
f1bd5fe152
Merge pull request #90 from xeb/main
|
1 year ago |
|
Alex Cheema
|
f051ebe6e0
remove accidentally added files
|
1 year ago |
 Mark Kockerbeck
|
5eafd5a305
try/except for decode, #75
|
1 year ago |
|
Alex Cheema
|
faa1319470
disable chatgpt api integration test, github changed something in their mac runners? perhaps time to switch over to circleci like mlx
|
1 year ago |
|
Alex Cheema
|
67a1aaa823
check processes in github workflow
|
1 year ago |
|
Alex Cheema
|
9a3ac273a9
Merge pull request #77 from Cloud1590/main
|
1 year ago |
|
Alex Cheema
|
628d8679b0
force mlx inference engine in github workflow, where it defaults to tinygrad because it's running on 'model': 'Apple Virtual Machine 1', 'chip': 'Apple M1 (Virtual)'
|
1 year ago |
|
Alex Cheema
|
e856d7f7f9
log chatgpt integration test output from each process on github workflow failure
|
1 year ago |
 Mark Kockerbeck
|
d2fa7b247e
Showing the message only if successfully decoded, #75
|
1 year ago |
|
Mark Kockerbeck
|
f1cd5ae7a6
Merge branch 'main' of github.com:xeb/exo
|
1 year ago |
|
Mark Kockerbeck
|
4f5ab78d9d
Addressing issue #75 to avoid decoding binary packets
|
1 year ago |
|
Alex Cheema
|
5a23376059
add log_request middleware if DEBUG>=2 to chatgpt api to debug api issues, default always to llama-3.1-8b
|
1 year ago |
|
Alex Cheema
|
2084784470
per-request kv cache, remove all explicit reset functionality as it wasnt used. fixes #67
|
1 year ago |
|
Alex Cheema
|
dd8c5d63a9
add support for mistral nemo and mistral large
|
1 year ago |
|
Alex Cheema
|
03fe7a058c
more robust message parsing fixes #81
|
1 year ago |
