Wang, Yi A 76cc129796 remove block_scales which is not needed anymore ... Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>		2025-04-11 01:28:14 -07:00
..
attention	remove block_scales which is not needed anymore	2025-04-11 01:28:14 -07:00
awq	remove unused quantization code and enable awq/gptq int4	2025-03-22 19:37:20 -07:00
gptq	fix gptq issue	2025-03-22 20:58:50 -07:00
moe	add moe support, fix qwen/mistral/mixtral crash	2025-03-18 00:45:15 -07:00
__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	match the latest vllm_extension ops	2025-04-10 19:32:32 -07:00
layernorm.py	clean cuda/rocm code in hpu backend, enable flat_hpu	2025-03-14 01:25:31 -07:00
linear.py	clean cuda/rocm code in hpu backend, enable flat_hpu	2025-03-14 01:25:31 -07:00
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	fix incorrect output in qwen2 idefics if hpu graph is used	2025-03-21 01:01:37 -07:00
speculative.py	Add Gaudi Backend (#3055)	2025-02-28 12:14:58 +01:00
tensor_parallel.py	clean cuda/rocm code in hpu backend, enable flat_hpu	2025-03-14 01:25:31 -07:00