 Alex Cheema
|
c0534b67c3
Merge commit: trigger test
|
há 7 meses atrás |
|
Alex Cheema
|
063964aab3
remove redundant sample_logits, put back opaque status for process_prompt so we have a way of preemptively starting downloads
|
há 7 meses atrás |
|
Alex Cheema
|
804ad4705a
upgrade mlx
|
há 7 meses atrás |
|
Alex Cheema
|
c9ded9ba96
optimise networking, remove bloat
|
há 7 meses atrás |
|
Alex Cheema
|
64365d684f
one two and three m4 pro clusters
|
há 8 meses atrás |
|
Alex Cheema
|
9397464fad
add commit to results
|
há 8 meses atrás |
 Nel Nibcord
|
08912d1b64
Only collect topology if peers changed
|
há 8 meses atrás |
|
Alex Cheema
|
06c2e236b8
rip out stats bloat
|
há 8 meses atrás |
|
Alex Cheema
|
cb4615c95d
fix SendNewToken
|
há 8 meses atrás |
|
Alex Cheema
|
f55a53ae7e
one token at a time
|
há 8 meses atrás |
 Gary
|
25b4af70e0
Merge branch 'main' into runners
|
há 8 meses atrás |
 Alex Cheema
|
a93092105c
set max-generate-tokens to 250
|
há 8 meses atrás |
|
Alex Cheema
|
0c6ab35333
increase timeout of http request in bench.py up to 10 mins
|
há 8 meses atrás |
|
Alex Cheema
|
72be5e4bd5
Merge pull request #556 from exo-explore/fixtestmodelhelpers
|
há 8 meses atrás |
|
Alex Cheema
|
b0e079b36a
fix counts in testmodelhelpers
|
há 8 meses atrás |
|
Alex Cheema
|
e5d54c77a9
add llama-3.3-70b to 3 M4 Pro cluster
|
há 8 meses atrás |
|
Alex Cheema
|
2ff4638122
Merge remote-tracking branch 'origin/main' into runners
|
há 8 meses atrás |
|
Alex Cheema
|
342b5d8ac0
Merge pull request #555 from exo-explore/modelvariations
|
há 8 meses atrás |
|
Alex Cheema
|
a0bada3b2a
add llama-3.2-1b-8bit, llama-3.2-3b-8bit, llama-3.2-3b-bf16
|
há 8 meses atrás |
|
Alex Cheema
|
b6f2385c41
run llama-3.1-8b on 3 m4 pro cluster
|
há 8 meses atrás |
|
Alex Cheema
|
9472ab0d2c
t
|
há 8 meses atrás |
|
Alex Cheema
|
dbb7ad3c08
run with three m4 pro
|
há 8 meses atrás |
|
Alex Cheema
|
2abe57be21
grasping at straws
|
há 8 meses atrás |
|
Alex Cheema
|
eeecdcb409
try a different taskpolicy
|
há 8 meses atrás |
|
Alex Cheema
|
f9f76129a1
better bench system info
|
há 8 meses atrás |
|
Alex Cheema
|
8c6d37d9b8
m4 cluster test
|
há 8 meses atrás |
|
Alex Cheema
|
2f74ea112e
Merge pull request #542 from wbic16/fix-issue-458
|
há 8 meses atrás |
|
Alex Cheema
|
1194db6e65
m3
|
há 8 meses atrás |
|
Alex Cheema
|
8cb7327da2
re-enable m4 cluster run
|
há 8 meses atrás |
|
Alex Cheema
|
bba0aa0877
single node test 20
|
há 8 meses atrás |
