 Nirav Patel
|
9cf6818f10
Fix AMD device capabilities fields
|
1 年之前 |
 Alex Cheema
|
837ed5d980
Merge pull request #648 from exo-explore/modelasyncload
|
1 年之前 |
 Alex Cheema
|
9c1bea97e8
fix embed_tokens for last layer in qwen models
|
1 年之前 |
|
Alex Cheema
|
af171f06fa
propagate prompts to other nodes so they can display them, cleaner prompt/output output
|
1 年之前 |
|
Alex Cheema
|
edfa53a4c2
Merge pull request #646 from exo-explore/modelasyncload
|
1 年之前 |
|
Alex Cheema
|
4a5b80a958
make sure mlx stuff is on separate thread non blocking
|
1 年之前 |
|
Alex Cheema
|
92d1bc01de
Merge pull request #645 from exo-explore/modelasyncload
|
1 年之前 |
|
Alex Cheema
|
6662d5668c
load mlx model shard on mlx thread so it doesnt block
|
1 年之前 |
|
Alex Cheema
|
a0d673fa3a
Merge pull request #640 from exo-explore/simpledownload
|
1 年之前 |
|
Alex Cheema
|
7c649085a1
fix eta/speed for resuming an existing download, using the session downloaded bytes
|
1 年之前 |
|
Alex Cheema
|
90e0e2761f
ignore not_started progress updates
|
1 年之前 |
|
Alex Cheema
|
265586f7b4
set timeout on get too
|
1 年之前 |
|
Alex Cheema
|
4748bb7dc7
increase file download timeout to 30min
|
1 年之前 |
|
Alex Cheema
|
ae770db4f3
increase download chunks to 1MB
|
1 年之前 |
|
Alex Cheema
|
82f75d0ccf
increase hf download http timeout 15 mins for large downloads
|
1 年之前 |
|
Alex Cheema
|
295f41c5cc
increase bench job timeout to give enough time to download
|
1 年之前 |
|
Alex Cheema
|
19a27c5bfd
HF_HOME -> EXO_HOME
|
1 年之前 |
|
Alex Cheema
|
d7ca9b7732
show each node id in the tinychat topology viz
|
1 年之前 |
|
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
|
1 年之前 |
|
Alex Cheema
|
21586063f6
use llama-3.2-1b in tinygrad test
|
1 年之前 |
|
Alex Cheema
|
277d63d860
special case when a model doesnt have a model index file, then use wildcard for allow_patterns
|
1 年之前 |
|
Alex Cheema
|
74379ef671
log download logs with DEBUG>=6 very verbose
|
1 年之前 |
|
Alex Cheema
|
3c7bd48aa3
get rid of some more hf bloat
|
1 年之前 |
|
Alex Cheema
|
1df023023e
remove a lot of hf bloat
|
1 年之前 |
|
Alex Cheema
|
b89495f444
rewrite ShardDownloader, simplify significantly
|
1 年之前 |
|
Alex Cheema
|
903950f64e
Merge pull request #638 from exo-explore/deepseekv3fix
|
1 年之前 |
|
Alex Cheema
|
a3766f538a
add exception for mlx-community/DeepSeek-R1-3bit and mlx-community/DeepSeek-V3-3bit in tokenizers test
|
1 年之前 |
|
Alex Cheema
|
9711d632e0
Merge pull request #637 from exo-explore/deepseekv3fix
|
1 年之前 |
|
Alex Cheema
|
82ef086010
add deepseek-v3-3bit and deepseek-r1-3bit
|
1 年之前 |
|
Alex Cheema
|
55ea366932
fix post_init deepseek v3
|
1 年之前 |
