c67e553fd3
[moe] remove ops
2024-07-22 04:00:42 +00:00
783aafa327
[moe] full test for deepseek and mixtral (pp + sp to fix)
2024-07-19 07:32:56 +00:00
c8bf2681e3
[moe] clean legacy code
2024-07-19 07:32:01 +00:00
335ad3c6fb
[moe] implement tp
2024-07-19 07:30:17 +00:00
1b15cc97f5
[moe] add mixtral dp grad scaling when not all experts are activated
2024-07-19 07:30:14 +00:00
2431694564
[moe] implement transit between non moe tp and ep
2024-07-19 07:29:35 +00:00
61109c7843
[zero] solve hang
2024-07-19 07:29:07 +00:00
da39d21b71
[moe] support mixtral ( #5309 )
...
* [moe] add mixtral block for single expert
* [moe] mixtral block fwd support uneven ep
* [moe] mixtral block bwd support uneven ep
* [moe] add mixtral moe layer
* [moe] simplify replace
* [meo] support save sharded mixtral
* [meo] support load sharded mixtral
* [meo] support save sharded optim
* [meo] integrate moe manager into plug
* [meo] fix optimizer load
* [meo] fix mixtral layer
2024-02-07 19:21:02 +08:00
7cfed5f076
[feat] refactored extension module ( #5298 )
...
* [feat] refactored extension module
* polish
* polish
* polish
* polish
* polish
* polish
* polish
* polish
* polish
* polish
2024-01-25 17:01:48 +08:00
3c08f17348
[hotfix]: modify create_ep_hierarchical_group and add test ( #5032 )
...
* feat: modify create_ep_hierarchical_group args
* test: add ep tests
* fix: remove get_process_group_ranks
* fix: fix src_rank
2023-11-17 10:53:00 +08:00
724441279b
[moe]: fix ep/tp tests, add hierarchical all2all ( #4982 )
...
* fix: add warning for EP different behavior
* fix: use shard_data in ep & tp model
* to: add used_capacity
* fix: fix router test
* feat: add create_ep_node_group
* feat: add create_ep_hierarchical_group fn
* feat: add HierarchicalAllToAll
* test: add hierarchical all2all test
* fix: fix test errors
* fix: simplify create_ep_hierarchical_group
* fix: add hierarchical_alltoall arg
* fix: fix environ typo
* revert: revert process mesh order
* to: add todo mark
* fix: skip hierarchical_comm if torch < 1.13.1
2023-11-09 06:31:00 +00:00
dc003c304c
[moe] merge moe into main ( #4978 )
...
* update moe module
* support openmoe
2023-11-02 02:21:24 +00:00
hxwang