xjx471258437andxjx392321 9bd92ba0f6 Support PD disaggregation with different TP/DP size for Qwen3-Next (#16056) ...

Co-authored-by: xjx392321 <xjx392321@alibaba-inc.com>

2026-01-25 15:34:02 +08:00

..

ascend

…

configs

…

cpu

[CPU] Add 4D input support for ROPE in sgl-kernel (#9337)

2025-12-16 17:27:39 +08:00

ep

…

models

…

quant

…

xpu

…

double-sparsity-config-Llama-3.1-8B-Instruct.json

…

experiment_runner.py

…

kv_cache_scales_llama3_1_8b.json

…

kv_cache_scales_llama3_8b.json

…

kv_cache_scales_qwen2_1_5b.json

…

parse_results.py

…

run_suite.py

…

test_deepseek_v3_basic.py

…

test_deepseek_v3_cutedsl_4gpu.py

…

test_deepseek_v3_fp4_4gpu.py

Support symmetric memory pre-allocation to avoid fragmentation (#17089)

2026-01-23 17:57:04 +08:00

test_deepseek_v3_mtp.py

…

test_deepseek_v32_basic.py

…

test_deepseek_v32_mtp.py

…

test_disaggregation_aarch64.py

…

test_disaggregation_different_tp.py

…

test_disaggregation_dp_attention.py

…

test_disaggregation_hybrid_attention.py

Support PD disaggregation with different TP/DP size for Qwen3-Next (#16056)

2026-01-25 15:34:02 +08:00

test_disaggregation_pp.py

…

test_embed_interpolate_unittest.py

…

test_epd_disaggregation.py

fix(ci): apply MMMU retry logic to all affected test files (#17329)

2026-01-19 10:00:29 -08:00

test_fla_layernorm_guard.py

…

test_fp8_blockwise_gemm.py

…

test_gpt_oss_4gpu.py

…

test_mistral_large3_basic.py

…

test_multi_instance_release_memory_occupation.py

…

test_nvfp4_gemm.py

…

test_pp_single_node.py

…

test_prefill_delayer.py

…

test_profile_v2.py

…

test_release_memory_occupation.py

[test] Add mamba cache release/resume memory test (#14215)

2026-01-06 15:51:10 +08:00