yctseng0211 4a78031a71 [ROCM] Optimized deepseek-r1 model with rmsnorm + fp8 quant fusion (#12689) ...

should be clean after https://github.com/sgl-project/sglang/pull/13017 landed

2025-11-11 02:59:10 -08:00

..

test_autoround.py

Add support for AutoRound quantized models (#10153)

2025-10-27 18:17:29 +08:00

test_awq_dequant.py

Reorganize CI and test files (#9027)

2025-08-10 12:30:06 -07:00

test_awq.py

[ci] Try fixing broken CIs (#12317)

2025-10-29 01:13:51 -07:00

test_block_int8.py

Support true on-policy (#12058)

2025-10-25 10:23:42 +08:00

test_fp8_kernel.py

Reorganize CI and test files (#9027)

2025-08-10 12:30:06 -07:00

test_fp8_kvcache.py

Reorganize CI and test files (#9027)

2025-08-10 12:30:06 -07:00

test_fused_rms_fp8_group_quant.py

[ROCM] Optimized deepseek-r1 model with rmsnorm + fp8 quant fusion (#12689)

2025-11-11 02:59:10 -08:00

test_int8_kernel.py

Support true on-policy (#12058)

2025-10-25 10:23:42 +08:00

test_triton_scaled_mm.py

Support Triton FP8 Gemm can handle hidden_dim not divisible by 16 (#9093)

2025-08-12 21:21:55 -07:00

test_w4a8_deepseek_v3.py

[2/N]Support DeepSeek-R1 w4a8 low latency deepep (#8464)

2025-10-24 17:41:16 -07:00

test_w8a8_quantization.py

[Fix] MoE: fix w8a8_fp8 MoE and add tests to cover this code path (#10429)

2025-09-14 17:34:28 -07:00