Keep the original checkpoint key names and fix Qwen4 vLLM inference #2327
fix
62a687c9
wenhuach21
changed the title fix Fix Qwen4 layer_type changed by Transformers, causing vLLM inference failure 46 days ago
update
de9384fd
Merge branch 'main' into fix_qwen4
832e543d
update
99e0afa4
Merge branch 'fix_qwen4' of https://github.com/intel/auto-round into …
e9373df8
update
85df591f
update
d172dd58
try to fix rename issue
dd0bb782
try to fix rename issue
d8554822
[pre-commit.ci] auto fixes from pre-commit.com hooks
1795e7f9
try to fix ngram shard rename issue
e9a2b541
Merge branch 'fix_qwen4' of https://github.com/intel/auto-round into …
09745d3c
[pre-commit.ci] auto fixes from pre-commit.com hooks
e5f4f2ea
wenhuach21
changed the title Fix Qwen4 layer_type changed by Transformers, causing vLLM inference failure Keep the original checkpoint key names and fix Qwen4 vLLM inference 45 days ago
update ignore layers
98de3ed5
Merge branch 'fix_qwen4' of https://github.com/intel/auto-round into …
043b00fb
update readme
670e61b0
[pre-commit.ci] auto fixes from pre-commit.com hooks
e0c009e0
wenhuach21
deleted the fix_qwen4 branch 44 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub