File tree Expand file tree Collapse file tree 2 files changed +3
-1
lines changed Expand file tree Collapse file tree 2 files changed +3
-1
lines changed Original file line number Diff line number Diff line change @@ -5,6 +5,9 @@ meta-llama/Llama-3.3-70B-Instruct:
55 accuracy : 45.55
66 - quant_algo : FP8
77 accuracy : 48.03
8+ - quant_algo : FP8
9+ kv_cache_quant_algo : FP8
10+ accuracy : 48.03
811deepseek-ai/DeepSeek-R1 :
912 - quant_algo : NVFP4
1013 accuracy : 70.45
Original file line number Diff line number Diff line change @@ -264,7 +264,6 @@ accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen
264264accuracy/test_llm_api.py::TestLlama3_2_1B::test_int4_awq_int8_kv_cache SKIP (https://nvbugs/5433541)
265265accuracy/test_llm_api.py::TestLlama3_2_1B::test_fp8_pp2 SKIP (https://nvbugs/5433541)
266266accuracy/test_cli_flow.py::TestLlama3_3_70BInstruct::test_fp8_prequantized_tp4 SKIP (https://nvbugs/5409414)
267- accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_tp4 SKIP (https://nvbugs/5409414)
268267accuracy/test_llm_api_pytorch.py::TestPhi4MM::test_auto_dtype SKIP (https://nvbugs/5433543)
269268accuracy/test_llm_api_pytorch.py::TestPhi4MM::test_auto_dtype_long_rope SKIP (https://nvbugs/5433543)
270269accuracy/test_llm_api_pytorch.py::TestPhi4MiniInstruct::test_auto_dtype SKIP (https://nvbugs/5433545)
You can’t perform that action at this time.
0 commit comments