 Alex Cheema
|
141de0d011
increase chatgpt api response timeout to 900 seconds
|
5 months ago |
 Alex Cheema
|
837ed5d980
Merge pull request #648 from exo-explore/modelasyncload
|
5 months ago |
|
Alex Cheema
|
9c1bea97e8
fix embed_tokens for last layer in qwen models
|
5 months ago |
|
Alex Cheema
|
af171f06fa
propagate prompts to other nodes so they can display them, cleaner prompt/output output
|
5 months ago |
|
Alex Cheema
|
edfa53a4c2
Merge pull request #646 from exo-explore/modelasyncload
|
5 months ago |
|
Alex Cheema
|
4a5b80a958
make sure mlx stuff is on separate thread non blocking
|
5 months ago |
|
Alex Cheema
|
92d1bc01de
Merge pull request #645 from exo-explore/modelasyncload
|
5 months ago |
|
Alex Cheema
|
6662d5668c
load mlx model shard on mlx thread so it doesnt block
|
5 months ago |
|
Alex Cheema
|
a0d673fa3a
Merge pull request #640 from exo-explore/simpledownload
|
5 months ago |
|
Alex Cheema
|
7c649085a1
fix eta/speed for resuming an existing download, using the session downloaded bytes
|
5 months ago |
|
Alex Cheema
|
90e0e2761f
ignore not_started progress updates
|
5 months ago |
|
Alex Cheema
|
265586f7b4
set timeout on get too
|
5 months ago |
|
Alex Cheema
|
4748bb7dc7
increase file download timeout to 30min
|
5 months ago |
|
Alex Cheema
|
ae770db4f3
increase download chunks to 1MB
|
5 months ago |
|
Alex Cheema
|
82f75d0ccf
increase hf download http timeout 15 mins for large downloads
|
5 months ago |
|
Alex Cheema
|
295f41c5cc
increase bench job timeout to give enough time to download
|
5 months ago |
|
Alex Cheema
|
19a27c5bfd
HF_HOME -> EXO_HOME
|
5 months ago |
|
Alex Cheema
|
d7ca9b7732
show each node id in the tinychat topology viz
|
5 months ago |
|
Alex Cheema
|
b349e48b0d
fix visual bug where frontend would show the full hf repo size, but in some cases that includes redundant files so we should use the model index in those cases too
|
5 months ago |
|
Alex Cheema
|
21586063f6
use llama-3.2-1b in tinygrad test
|
5 months ago |
|
Alex Cheema
|
277d63d860
special case when a model doesnt have a model index file, then use wildcard for allow_patterns
|
5 months ago |
|
Alex Cheema
|
74379ef671
log download logs with DEBUG>=6 very verbose
|
5 months ago |
|
Alex Cheema
|
3c7bd48aa3
get rid of some more hf bloat
|
5 months ago |
|
Alex Cheema
|
1df023023e
remove a lot of hf bloat
|
5 months ago |
|
Alex Cheema
|
b89495f444
rewrite ShardDownloader, simplify significantly
|
5 months ago |
|
Alex Cheema
|
903950f64e
Merge pull request #638 from exo-explore/deepseekv3fix
|
5 months ago |
|
Alex Cheema
|
a3766f538a
add exception for mlx-community/DeepSeek-R1-3bit and mlx-community/DeepSeek-V3-3bit in tokenizers test
|
5 months ago |
|
Alex Cheema
|
9711d632e0
Merge pull request #637 from exo-explore/deepseekv3fix
|
5 months ago |
|
Alex Cheema
|
82ef086010
add deepseek-v3-3bit and deepseek-r1-3bit
|
5 months ago |
|
Alex Cheema
|
55ea366932
fix post_init deepseek v3
|
5 months ago |
