Wang, Yi 533eee50dc forward and tokenize chooser use the same shape (#3196) ... * forward and tokenize chooser use the same shape concate or filter happened to cpu tensor to avoid dynamic shape in hpu Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> * use hpu set seed Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> --------- Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>		2025-05-06 10:49:32 +02:00
..
attention	forward and tokenize chooser use the same shape (#3196)	2025-05-06 10:49:32 +02:00
awq	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
gptq	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
moe	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
__init__.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
bnb.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
conv.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
exl2.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
fp8.py	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
layernorm.py	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
linear.py	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
lora.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
medusa.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
mlp.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
rotary.py	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00
speculative.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
tensor_parallel.py	Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)	2025-04-14 15:58:13 +02:00