Alex Cheema
|
84dfc8a738
|
Fast memory profiling
Co-authored-by: Evan <evanev7@gmail.com>
|
2025-10-07 16:23:51 +01:00 |
|
Alex Cheema
|
e01f9cf739
|
Disable build macos app
|
2025-10-07 15:39:15 +01:00 |
|
Alex Cheema
|
35ab6b376e
|
fix: master tests
Co-authored-by: Evan <evanev7@gmail.com>
|
2025-10-07 15:36:05 +01:00 |
|
Evan Quiney
|
962e5ef40d
|
version bump for brew consistency
|
2025-10-07 15:18:54 +01:00 |
|
Evan Quiney
|
b1721e941b
|
nix cleanup
|
2025-10-01 09:47:00 +01:00 |
|
Evan Quiney
|
22f0ca2a59
|
FIX: OpenWebUI compat
|
2025-09-30 16:28:38 +01:00 |
|
Evan Quiney
|
57486a4305
|
kill go
Fairwell Gelu, Chief Lunch Officer
|
2025-09-30 11:10:55 +01:00 |
|
Evan Quiney
|
38ff949bf4
|
big refactor
Fix. Everything.
Co-authored-by: Andrei Cravtov <the.andrei.cravtov@gmail.com>
Co-authored-by: Matt Beton <matthew.beton@gmail.com>
Co-authored-by: Alex Cheema <alexcheema123@gmail.com>
Co-authored-by: Seth Howes <sethshowes@gmail.com>
|
2025-09-30 11:03:04 +01:00 |
|
Matt Beton
|
7040c9508f
|
Multiprocessing Runner
|
2025-09-17 09:31:49 +01:00 |
|
Matt Beton
|
35c4311587
|
Dashboard Status & Bugfixes
|
2025-08-29 17:34:17 +01:00 |
|
Matt Beton
|
a33787f5fd
|
Prompt length
|
2025-08-29 16:07:36 +01:00 |
|
Matt Beton
|
1b8b456ced
|
full mlx caching implementation
|
2025-08-26 17:15:08 +01:00 |
|
Matt Beton
|
84c90a6d35
|
feat: mlx memory cache for faster ttft
Co-authored-by: Evan <evanev7@gmail.com>
Co-authored-by: s17 <s17@s17s-Mac-Studio.local>
|
2025-08-26 13:05:42 +01:00 |
|
Evan Quiney
|
5efe5562d7
|
feat: single entrypoint and logging rework
|
2025-08-26 11:08:09 +01:00 |
|
Andrei Cravtov
|
ef5c5b9654
|
changes include: ipc, general utilities, flakes stuff w/ just, autopull script
|
2025-08-25 17:33:40 +01:00 |
|
Alex Cheema
|
5bfc99b415
|
add EXO logo to dashboard
|
2025-08-25 16:41:13 +01:00 |
|
Evan Quiney
|
11f8b4ef33
|
tidy: fix justfile, run.sh, run formatter
|
2025-08-21 18:44:53 +01:00 |
|
Evan Quiney
|
be6f5ae7f1
|
feat: build system and homebrew compatibility
|
2025-08-21 16:07:37 +01:00 |
|
Evan Quiney
|
40efed4436
|
unvendored macmon
|
2025-08-20 13:04:46 +01:00 |
|
Gelu Vrabie
|
ea9e573409
|
Refactor runner supervisor
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-08-18 18:37:52 +01:00 |
|
Gelu Vrabie
|
345fafd80d
|
Forwarder versioning
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-08-18 15:08:50 +01:00 |
|
Evan Quiney
|
ea3eeea826
|
improved go caching with nix
Co-authored-by: Gelu Vrabie <gelu.vrabie.univ@gmail.com>
|
2025-08-15 15:24:58 +01:00 |
|
Gelu Vrabie
|
a2a37c0ebe
|
discovery fixed
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-08-15 15:23:20 +01:00 |
|
Gelu Vrabie
|
57073f35c3
|
collection of fixes for Shanghai demo
Co-authored-by: Matt Beton <matthew.beton@gmail.com>
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-08-15 15:21:51 +01:00 |
|
Andrei Cravtov
|
7e19804aa5
|
Integrate flake parts
|
2025-08-13 09:55:22 +01:00 |
|
Matt Beton
|
dbcd09aa53
|
No 70b
|
2025-08-12 18:42:27 +01:00 |
|
Matt Beton
|
c1d5b381f4
|
70B model unit test only runs if its downloaded
|
2025-08-07 10:41:56 +01:00 |
|
Alex Cheema
|
473512ddd0
|
r1 size
|
2025-08-04 22:57:31 +08:00 |
|
Alex Cheema
|
817c5993f0
|
fix dem model cards yo
|
2025-08-04 22:56:06 +08:00 |
|
Gelu Vrabie
|
75ecda55a9
|
fix gitignore
Co-authored-by: Matt Beton <matthew.beton@gmail.com>
|
2025-08-04 13:49:49 +01:00 |
|
Alex Cheema
|
c560c55c4e
|
build and release on staging
|
2025-08-04 07:41:09 +08:00 |
|
Sami Khan
|
f51f8f72f8
|
app launches python modules
|
2025-08-04 06:18:31 +08:00 |
|
Seth Howes
|
407796d18f
|
Minor dashboard fixes
|
2025-08-04 06:15:01 +08:00 |
|
Alex Cheema
|
6daf7f31f7
|
clean model cards
|
2025-08-04 05:31:30 +08:00 |
|
Alex Cheema
|
f352ddfc5f
|
run configure_mlx.sh in run.sh
|
2025-08-04 03:59:42 +08:00 |
|
Alex Cheema
|
6855a7727d
|
set a 15 sec timeout for getting initial download progress
|
2025-08-03 20:37:20 +08:00 |
|
Matt Beton
|
1fe4ed3442
|
Worker Exception & Timeout Refactor
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
Co-authored-by: Alex Cheema <alexcheema123@gmail.com>
Co-authored-by: Seth Howes <sethshowes@gmail.com>
|
2025-08-02 08:28:37 -07:00 |
|
Alex Cheema
|
92c9688bf0
|
Remove rust
|
2025-08-02 08:16:39 -07:00 |
|
Sami Khan
|
a46f8c3cd1
|
app
Co-authored-by: Alex Cheema <alexcheema123@gmail.com>
|
2025-08-01 19:14:27 -07:00 |
|
Seth Howes
|
71bafabc63
|
Dashboard with instances
|
2025-08-01 14:38:07 +01:00 |
|
Gelu Vrabie
|
0e32599e71
|
fix libp2p + other prs that were wrongly overwritten before (111,112,117,118,1119 + misc commits from Alex)
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
Co-authored-by: Alex Cheema <41707476+AlexCheema@users.noreply.github.com>
Co-authored-by: Seth Howes <71157822+sethhowes@users.noreply.github.com>
Co-authored-by: Matt Beton <matthew.beton@gmail.com>
Co-authored-by: Alex Cheema <alexcheema123@gmail.com>
|
2025-07-31 20:36:47 +01:00 |
|
Alex Cheema
|
2031d9481d
|
fix api get_state
|
2025-07-30 07:15:15 -07:00 |
|
Matt Beton
|
b350ededb2
|
Test Supervisor Errors.
|
2025-07-30 13:30:54 +01:00 |
|
Gelu Vrabie
|
ff3d11c748
|
just run
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-07-29 16:58:27 +01:00 |
|
Gelu Vrabie
|
25fa46c6f6
|
Update CODEOWNERS
|
2025-07-29 13:08:29 +01:00 |
|
Seth Howes
|
3f192f20cc
|
Reinstate dashboard
|
2025-07-28 23:18:23 +01:00 |
|
Alex Cheema
|
a2b4093d25
|
add metrics: gpu_usage, temp, sys_power, pcpu_usage, ecpu_usage, ane_…
|
2025-07-28 23:02:33 +01:00 |
|
Alex Cheema
|
12566865d5
|
better profiling
|
2025-07-28 22:15:04 +01:00 |
|
Gelu Vrabie
|
b88abf1cc2
|
fix topology disconnects and add heartbeat
Co-authored-by: Gelu Vrabie <gelu@exolabs.net>
|
2025-07-28 22:00:05 +01:00 |
|
Alex Cheema
|
dbd0bdc34b
|
fix ci linter
|
2025-07-28 20:12:48 +01:00 |
|