 Alex Cheema
|
aa7cd34b51
Merge pull request #323 from lipere123/adalovace
|
9 달 전 |
 lipere123
|
6c302244e0
Merge branch 'exo-explore:main' into adalovace
|
9 달 전 |
|
Alex Cheema
|
9a93dcc414
Merge pull request #329 from varshith15/llava_broken_fix
|
9 달 전 |
 Varshith
|
0730532351
fix: tokenize
|
9 달 전 |
|
Alex Cheema
|
0f272f53b8
Merge pull request #326 from exo-explore/fix_llama_embed_tokens
|
9 달 전 |
 Alex Cheema
|
17065d879b
dynamic halfway partition point in unit test
|
9 달 전 |
|
Alex Cheema
|
ae74d2da16
run unit test on llama 3.2 1b for faster test
|
9 달 전 |
|
Alex Cheema
|
ad09b4b3d9
also initialize embed_tokens if last layer and tie_word_embeddings true
|
9 달 전 |
|
Alex Cheema
|
fbc407c6ae
make llama-3.2-1b the default for tests so they run faster
|
9 달 전 |
|
Alex Cheema
|
8950d95ef8
updgrade all mac ci jobs to xcode=16.0.0, resource_class=m2pro.large
|
9 달 전 |
 LIPERE Benjamin
|
ade9db4dfd
feat(device_capabilities.py): add support for NVIDIA RTX 4000 ADA generation device capabilities
|
9 달 전 |
|
Alex Cheema
|
c1a26cd7fa
Merge pull request #315 from GaetanLepage/a6000-flops
|
9 달 전 |
 Gaetan Lepage
|
a0ad18c6ad
Fix GPU names for RTX Ampere cards
|
9 달 전 |
|
Alex Cheema
|
eade4fb62d
Merge pull request #310 from exo-explore/udp_discovry_peer_race_condition
|
9 달 전 |
|
Alex Cheema
|
8a69a7a238
one line print
|
9 달 전 |
|
Alex Cheema
|
b7996b9af4
race condition in on_listen_message for udp discovery fixes #308
|
9 달 전 |
|
Alex Cheema
|
27e5ee6b22
Merge pull request #309 from exo-explore/cleanup_peers_race_condition
|
9 달 전 |
|
Alex Cheema
|
e80ee60760
fix the race condition in cleanup peers and run the peer checks concurrently. fixes #308
|
9 달 전 |
|
Alex Cheema
|
48fe7b9130
Merge pull request #306 from exo-explore/process_prompt_shield
|
9 달 전 |
|
Alex Cheema
|
aa20562614
shield process_prompt so downloads dont get cancelled when chatgpt api request times out
|
9 달 전 |
|
Alex Cheema
|
7b2a523fd1
Merge pull request #289 from GaetanLepage/pynvml
|
10 달 전 |
|
Alex Cheema
|
db123884e9
Merge pull request #291 from vanakema/main
|
10 달 전 |
|
Alex Cheema
|
33c0dd8583
Merge pull request #292 from exo-explore/remove_tailscale_package_dependency
|
10 달 전 |
|
Alex Cheema
|
e8a8702377
replace tailscale.devices with good old http, removing the need for tailscale dependency
|
10 달 전 |
 Mark Van Aken
|
82c7ce69f6
Point `llama-3.1-70b-bf16` model to the actually bf16 version
|
10 달 전 |
|
Gaetan Lepage
|
9ffd8116f0
Use official nvidia-ml-py instead of pynvml
|
10 달 전 |
|
Alex Cheema
|
2b9dec20eb
Merge pull request #282 from exo-explore/unsilence_errors
|
10 달 전 |
|
Alex Cheema
|
9b9f40d470
only stream results for the same request id. this allows multiple concurrent requests on the same LLM without overlapping interference in the streamed outputs
|
10 달 전 |
|
Alex Cheema
|
9223993e29
await node process_prompt with timeoout
|
10 달 전 |
|
Alex Cheema
|
5e0db20426
Merge pull request #278 from exo-explore/peer_prio
|
10 달 전 |
