 Alex Cheema
|
953bce4642
simple benchmarking script that measures TTFT and TPS
|
7 months ago |
|
Alex Cheema
|
87f601297e
remove old cache code mlx
|
7 months ago |
|
Alex Cheema
|
ec85bc2546
add a way to stream the output from exo run
|
7 months ago |
|
Alex Cheema
|
fe0f1cdb1e
fix shutdown
|
7 months ago |
|
Alex Cheema
|
d3505e03e2
run tests with --disable-tui for faster tests
|
7 months ago |
|
Alex Cheema
|
8a741485df
fix test_inference_engine unittest reshape token output tensor
|
7 months ago |
 Alex Cheema
|
7013041e1e
Merge pull request #484 from blindcrone/grpc-fix
|
7 months ago |
 Nel Nibcord
|
e3ec9eaa44
Fixed GRPC issues
|
7 months ago |
|
Alex Cheema
|
93d38e2bf7
Merge pull request #482 from exo-explore/is_finished_fixes
|
7 months ago |
|
Alex Cheema
|
72c3fdab46
fix end of request behaviour and add back broadcasting tokens to other nodes
|
7 months ago |
|
Alex Cheema
|
c77355238d
target_shard to next_shard
|
7 months ago |
|
Alex Cheema
|
077da36bad
Merge pull request #481 from roryclear/ui
|
7 months ago |
 Rory Clear
|
46a8e8fc81
typo
|
7 months ago |
|
Rory Clear
|
c78973660a
new tinychat ui
|
7 months ago |
|
Alex Cheema
|
822a014433
Merge pull request #462 from blindcrone/refactor-messaging
|
7 months ago |
|
Nel Nibcord
|
8f78c7819e
Refactors to simplify messaging and properly batch inputs
|
7 months ago |
|
Alex Cheema
|
1fa42f3063
typo
|
7 months ago |
|
Alex Cheema
|
0501efa6cd
Merge pull request #470 from josh1593/package-exo-app
|
7 months ago |
 josh
|
520d9d1164
error fix
|
7 months ago |
|
josh
|
9489b99c07
typo
|
7 months ago |
|
josh
|
aae23cecdf
build error fix
|
7 months ago |
 josh
|
dda0d08a9b
Merge branch 'main' into package-exo-app
|
7 months ago |
 dependabot[bot]
|
c82d164868
Bump aiohttp from 3.10.2 to 3.10.11
|
7 months ago |
|
Alex Cheema
|
1b7e67832c
fix modelpool, add tests in test/test_model_helpers.py
|
7 months ago |
|
Alex Cheema
|
559f12e7d0
check if user has read/write access to HF_HOME and warn them if not
|
7 months ago |
|
Alex Cheema
|
3022aab994
remove redundant dummy import
|
7 months ago |
|
Alex Cheema
|
0ab302a35f
add --default-model command line arg
|
7 months ago |
|
Alex Cheema
|
2dafa9cc65
Merge pull request #472 from exo-explore/pyver
|
7 months ago |
|
Alex Cheema
|
312602fa13
fix shard_specific_patterns
|
7 months ago |
|
Alex Cheema
|
4ece73423e
always run tinygrad stuff on same thread. tricky because of lazy evaluation
|
7 months ago |
