 James Alexander Shield
|
b39a251d3e
fix: remove extraneous '/'
|
hai 10 meses |
|
James Shield
|
a0024fd421
feat: support HF_ENDPOINT base url ENV VAR
|
hai 11 meses |
 Alex Cheema
|
db9f44d16d
website link
|
hai 11 meses |
|
Alex Cheema
|
6c875dcc81
update hiring link
|
hai 11 meses |
|
Alex Cheema
|
074228e326
update README with hiring
|
hai 11 meses |
|
Alex Cheema
|
198cd6fb17
trigger ci
|
hai 11 meses |
|
Alex Cheema
|
20522e0638
update docs to make tinygrad usage clearer
|
hai 11 meses |
 Alex Cheema
|
e0ed9170db
Merge pull request #209 from GaetanLepage/used-ports
|
hai 11 meses |
 Gaetan Lepage
|
4b009401f9
move `.exo_used_ports` to `/tmp`
|
hai 11 meses |
|
Alex Cheema
|
0fa15367f7
Merge pull request #208 from exo-explore/broken_links_readme
|
hai 11 meses |
|
Alex Cheema
|
ca64456260
fix broken links in README
|
hai 11 meses |
|
Alex Cheema
|
87e08f89f1
Merge pull request #203 from exo-explore/non_blocking
|
hai 11 meses |
|
Alex Cheema
|
874886abc4
simplify mlx non blocking
|
hai 11 meses |
|
Alex Cheema
|
e616d4e86b
run realize on the result in tinygrad
|
hai 11 meses |
|
Alex Cheema
|
9345684b38
closely match prev impl mlx non blocking
|
hai 11 meses |
|
Alex Cheema
|
d6e661fd69
match previous impl with np.array in mlx
|
hai 11 meses |
|
Alex Cheema
|
caf9b57a2a
trigger ci
|
hai 11 meses |
|
Alex Cheema
|
84187113de
add a test for hf get_weight_map
|
hai 11 meses |
|
Alex Cheema
|
4ec613d4e8
simplify tinygrad non blocking
|
hai 11 meses |
|
Alex Cheema
|
6342384df4
Merge branch 'main' into non_blocking
|
hai 11 meses |
|
Alex Cheema
|
a1a0ffac55
add tinychat option for llama-3.1-70b-bf16
|
hai 11 meses |
|
Alex Cheema
|
de19f0ab42
Merge branch 'main' into non_blocking
|
hai 11 meses |
|
Alex Cheema
|
2948a83448
add llama-3.1-70b-bf16 model option
|
hai 11 meses |
|
Alex Cheema
|
11dd952d26
use set for shard specific patterns
|
hai 11 meses |
|
Alex Cheema
|
ea3322dea4
remove comment
|
hai 11 meses |
|
Alex Cheema
|
e0fda94d20
use sets for shard specific patterns
|
hai 11 meses |
|
Alex Cheema
|
b239c8a6d0
Merge branch 'main' into non_blocking
|
hai 11 meses |
|
Alex Cheema
|
8f65e1e697
fix weight_map resolution. previously we were always defaulting to allow pattern *.safetensors
|
hai 11 meses |
|
Alex Cheema
|
6881722b72
simplify non-blocking mlx inference
|
hai 11 meses |
|
Alex Cheema
|
9db16f8dca
use a queue for non-blocking mlx inference
|
hai 11 meses |
