[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799)
Co-authored-by: beagleski <yunanzhang@microsoft.com> Co-authored-by: bapatra <bapatra@microsoft.com> Co-authored-by: Barun Patra <codedecde@users.noreply.github.com> Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
co-authored by
beagleski
bapatra
Barun Patra
Michael Goin
parent
e64fde4b01
commit
8e192ff967
@@ -56,6 +56,7 @@ _GENERATION_MODELS = {
|
||||
"Starcoder2ForCausalLM": ("starcoder2", "Starcoder2ForCausalLM"),
|
||||
"ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
|
||||
"XverseForCausalLM": ("xverse", "XverseForCausalLM"),
|
||||
"Phi3SmallForCausalLM": ("phi3_small", "Phi3SmallForCausalLM"),
|
||||
}
|
||||
|
||||
_EMBEDDING_MODELS = {
|
||||
|
||||
Reference in New Issue
Block a user