 Alex Cheema
|
788c49784c
retry fetch_file_list also
|
1 year ago |
|
Alex Cheema
|
6b1c8635fc
ensure exo dir on start, retry with exp backoff on file downloads
|
1 year ago |
 Alex Cheema
|
24c410c19c
Merge pull request #653 from exo-explore/tinyfixes
|
1 year ago |
|
Alex Cheema
|
f6ed830ba6
Merge pull request #651 from exo-explore/parallelise_model_loadin
|
1 year ago |
|
Alex Cheema
|
e6b4f2993c
fix prompt output spacing in tui
|
1 year ago |
 DeftDawg
|
a25e02c913
Add 4-bit to the end of DeepSeek V3/R1 model descriptions
|
1 year ago |
|
Alex Cheema
|
3675804f4d
throttle repo progress events and only send them out if something changed
|
1 year ago |
|
Alex Cheema
|
96f1aecb05
only in_progress if any given file is in_progress
|
1 year ago |
|
Alex Cheema
|
23a5030604
even if part of a file is downloaded it may not be in_progress
|
1 year ago |
|
Alex Cheema
|
31b56e862f
make a singleton thread pool executor for tinygrad since we always want it to run on the same thread
|
1 year ago |
|
Alex Cheema
|
9f6c688d62
update tinygrad
|
1 year ago |
|
Alex Cheema
|
4887be5103
parallelise model loading
|
1 year ago |
|
Alex Cheema
|
75091e206b
Merge pull request #650 from exo-explore/chatgpttimeout
|
1 year ago |
|
Alex Cheema
|
141de0d011
increase chatgpt api response timeout to 900 seconds
|
1 year ago |
|
Alex Cheema
|
263b18a31e
Merge pull request #649 from eclecticc/amd_fix
|
1 year ago |
 Nirav Patel
|
9cf6818f10
Fix AMD device capabilities fields
|
1 year ago |
|
Alex Cheema
|
837ed5d980
Merge pull request #648 from exo-explore/modelasyncload
|
1 year ago |
|
Alex Cheema
|
9c1bea97e8
fix embed_tokens for last layer in qwen models
|
1 year ago |
|
Alex Cheema
|
af171f06fa
propagate prompts to other nodes so they can display them, cleaner prompt/output output
|
1 year ago |
|
Alex Cheema
|
edfa53a4c2
Merge pull request #646 from exo-explore/modelasyncload
|
1 year ago |
|
Alex Cheema
|
4a5b80a958
make sure mlx stuff is on separate thread non blocking
|
1 year ago |
|
Alex Cheema
|
92d1bc01de
Merge pull request #645 from exo-explore/modelasyncload
|
1 year ago |
|
Alex Cheema
|
6662d5668c
load mlx model shard on mlx thread so it doesnt block
|
1 year ago |
|
Alex Cheema
|
a0d673fa3a
Merge pull request #640 from exo-explore/simpledownload
|
1 year ago |
|
Alex Cheema
|
7c649085a1
fix eta/speed for resuming an existing download, using the session downloaded bytes
|
1 year ago |
|
Alex Cheema
|
90e0e2761f
ignore not_started progress updates
|
1 year ago |
|
Alex Cheema
|
265586f7b4
set timeout on get too
|
1 year ago |
|
Alex Cheema
|
4748bb7dc7
increase file download timeout to 30min
|
1 year ago |
|
Alex Cheema
|
ae770db4f3
increase download chunks to 1MB
|
1 year ago |
|
Alex Cheema
|
82f75d0ccf
increase hf download http timeout 15 mins for large downloads
|
1 year ago |
