Andreas Karatzas 9f0247cfa4

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

2025-11-11 18:34:36 -08:00

..

__init__.py

…

fp_quant.py

…

reference_mxfp4.py

…

test_auto_round.py

…

test_blackwell_moe.py

[BugFix][Performance] Restore flashinfer autotuning for all scenarios (#27904)

2025-11-04 15:56:21 +08:00

test_compressed_tensors.py

[1/N][Platform] Cleanup useless function (#26982)

2025-10-22 09:04:57 +00:00

test_configs.py

…

test_cpu_offload.py

…

test_experts_int8.py

…

test_fp8.py

[CI Failure] nm-testing/Qwen2-0.5B-Instruct-FP8-SkipQKV was removed from HF. Skip it in tests (#28170)

2025-11-06 01:22:13 +00:00

test_gptq_dynamic.py

…

test_gptq_v2.py

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

test_ipex_quant.py

…

test_lm_head.py

…

test_mixed_precision.py

[ROCm][Quantization] extend AMD Quark to support mixed-precision quantized model (#24239)

2025-11-11 12:05:22 -05:00

test_modelopt.py

…

test_ptpc_fp8.py

…

test_quark.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

test_register_quantization_config.py

…

test_rtn.py

…

test_torchao.py

Support using Int4PreshuffledTensor after loading (#26066)

2025-11-04 06:00:57 -05:00

utils.py

…