Default Branch

main

2ad0b2b936 · Fix p2p pushing in rpc_inference (by @miaoqijun ) , support transformers 4.38.2 (#563) · Updated 2 weeks ago

Branches

mixtral

91b1e2a27b · fix order of init · Updated 3 hours ago

0
9
forward_backward

26d4cd855d · 2 · Updated 2 weeks ago

1
4
peft_update

96b95609be · style · Updated 3 weeks ago

1
6
fix-docker

6626f8ecc2 · Update push-docker-test2.yaml · Updated 1 month ago

2
3
forward_kwargs

3195579620 · Merge remote-tracking branch 'origin/main' into forward_kwargs · Updated 4 months ago

3
40
bump

313992eb38 · (temporary) bump version · Updated 4 months ago

3
1
test_main

b6eb38eb85 · test rebuild · Updated 5 months ago

7
1
fix-inference-retry

63282afb4e · Try 5% fails · Updated 5 months ago

7
1
lora_from_hub

1b21dd3217 · Add memory cache usage · Updated 7 months ago

14
2
payload-size

b945e388e5 · Remove smaller limit for legacy bfloat16 serialization · Updated 7 months ago

14
1
partial_rollback

cc4fe17a99 · minimize diff · Updated 7 months ago

14
19
qkv_merge

4159e557bf · Create dummy data when materializing qkv_proj · Updated 7 months ago

17
8
no_qkv_merge

a7f87b636b · Disable the optimization · Updated 7 months ago

17
4
wip_triton

fa464dfc99 · WIP Triton+QKV merge · Updated 7 months ago

17
1
hivemind-dht-fork-process

c17b2fbcaf · [don't merge] Test with hivemind@dht-fork-process branch · Updated 7 months ago

20
1
repetition-penalty

dd677d9e76 · Merge branch 'main' into repetition-penalty · Updated 8 months ago

42
2
amd-gpus

1ba721d51e · Merge branch 'main' into amd-gpus · Updated 8 months ago

48
7
bnb-0-41-1

16e6ce95e8 · Merge branch 'main' into bnb-0-41-1 · Updated 8 months ago

52
2
lru

cc67c332a6 · the (still) reasonable version · Updated 8 months ago

72
1