patch copy gptq #642

Job	Run time
CodeQL Scan	3m 8s
Dependency Review	4s
Calculate Tests To Trigger	5s
Test / gsm8k_small_g3_tp1	7m 5s
Test / gsm8k_small_g3_tp2	6m 35s
Test / gsm8k_small_g2_tp1	1m 3s
Test / gsm8k_small_g2_tp2	3s
Test / gsm8k_large_g3_tp2	6m 24s
Test / gsm8k_large_g2_tp4	1m 2s
Test / gsm8k_small_g3_tp1_fp8	4m 20s
Test / gsm8k_small_g3_tp2_fp8	4m 28s
Test / gsm8k_small_g3_tp1_mss	5m 51s
Test / gsm8k_small_g2_tp1_mss	2m 20s
Test / gsm8k_small_g3_tp2_mss	5m 48s
Test / gsm8k_small_g2_tp2_mss	3s
Test / gsm8k_small_g2_tp1_spec_decode	2m 23s
Test / gsm8k_small_g2_tp1_mlp_spec_decode	52s
Test / gsm8k_small_g2_tp1_medusa_spec_decode	28s
Test / gsm8k_small_g2_tp1_eagle_spec_decode	1m 2s
Test / test_llama_lora	3s
Test / test_multilora	4s
Test / test_long_context	4s
Test / test_gptq	3s
Test / test_awq	5m 31s
	58m 49s

Provide feedback