sglang

accuracy

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375 )

2026-09-08 16:42:12 -07:00

disaggregation

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

perf

[AMD][CI] Add MiniMax-M3-MXFP8 MI35x nightly perf benchmark (#36142 )

2026-08-25 14:05:01 -07:00

conftest.py

[AMD] Fix the diffusion perf fixture lookup (#38686 )

2026-09-10 00:07:08 -07:00

test_deepseek_r1_hicache_mi35x.py

[Fix] Shut hicache test servers down gracefully before SIGKILL (#37194 )

2026-08-30 22:45:40 -07:00

test_deepseek_r1_mxfp4_8gpu.py

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375 )

2026-09-08 16:42:12 -07:00

test_deepseek_v3_basic_kv_fp8.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_deepseek_v3_basic.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_deepseek_v3_mtp_kv_fp8.py

Migrate all callers from /get_server_info to /server_info (#21463 )

2026-04-01 21:17:50 -07:00

test_deepseek_v3_mtp.py

[AMD] prepare for MI300x PR runner pool: registry mirror, runner routing, threshold tuning (#23156 )

2026-04-21 00:58:23 -07:00

test_deepseek_v4_flash_fp4.py

[AMD] deepseek-v4 clean env vars (#28920 )

2026-06-22 07:32:43 -07:00

test_deepseek_v4_flash_fp8_mi30x.py

[AMD][CI] Add DeepSeek-V4-Flash FP8 accuracy coverage on MI30x (#36396 )

2026-08-26 19:30:07 -07:00

test_deepseek_v4_flash_fp8_tbo.py

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375 )

2026-09-08 16:42:12 -07:00

test_deepseek_v4_flash_fp8.py

[AMD] deepseek-v4 clean env vars (#28920 )

2026-06-22 07:32:43 -07:00

test_deepseek_v4_pro_fp4_cp_tbo.py

[CP V1 Deprecation 3.5/5] Deprecate HIP/NPU/MUSA prefill CP and remove legacy implementation (#38293 )

2026-09-07 15:39:34 -07:00

test_deepseek_v4_pro_fp4_cp.py

[CP V1 Deprecation 3.5/5] Deprecate HIP/NPU/MUSA prefill CP and remove legacy implementation (#38293 )

2026-09-07 15:39:34 -07:00

test_deepseek_v4_pro_fp4_dspark.py

[AMD] Fix Dspark accept length and reduce host bubble on DSV4 (#39116 )

2026-09-12 15:21:43 -07:00

test_deepseek_v4_pro_fp4_mtp.py

[AMD] deepseek-v4 clean env vars (#28920 )

2026-06-22 07:32:43 -07:00

test_deepseek_v4_pro_fp4_tbo_mtp.py

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375 )

2026-09-08 16:42:12 -07:00

test_deepseek_v4_pro_fp4_tbo.py

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375 )

2026-09-08 16:42:12 -07:00

test_deepseek_v4_pro_fp4.py

[AMD] deepseek-v4 clean env vars (#28920 )

2026-06-22 07:32:43 -07:00

test_deepseek_v4_pro_fp8.py

[AMD] deepseek-v4 clean env vars (#28920 )

2026-06-22 07:32:43 -07:00

test_deepseek_v32_basic.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_deepseek_v32_mtp.py

[Refactor] Rename NSA → DSA: user-facing aliases, file/class/import rename (#25821 )

2026-05-20 00:18:04 -07:00

test_dsa_skip_logits_clean.py

[AMD] [GLM5] skip redundant -inf pre-fill of HIP indexer MQA-logits (#28757 )

2026-06-24 23:21:39 -07:00

test_dsv4_hip_bcg_metadata.py

[ROCm][DSV4] Enable breakable CUDA graph prefill (#37810 )

2026-09-16 08:52:11 -07:00

test_fp8_per_channel_detection.py

[ROCm/gfx95] Fix fp8 per-channel attention for Kimi-K2.7-code-mxfp4 o… (#31105 )

2026-08-11 00:51:57 -07:00

test_kimi_k2_instruct.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_kimi_k3_kda_inproj_fusion.py

[AMD] [Kimi-K3] Fuse the KDA input projection into a single GEMM on ROCm (#35176 )

2026-09-03 23:30:08 -07:00

test_kimi_k25_mxfp4_bcg_mi35x.py

[AMD] Rebalance stage-c-large-8-gpu-mi35x partitions to fix 60-min timeout (#29726 )

2026-07-01 08:17:00 -07:00

test_kimi_k25_mxfp4.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_moriep_small.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_qwen3_coder_next_8gpu.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_qwen3_instruct_fp8.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_qwen3_instruct_mxfp4.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_qwen3_instruct.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

test_unified_attention_3d_mtp.py

[AMD] Optimize Qwen3.5 MTP unified attention on gfx950 (#36330 )

2026-08-27 00:13:49 -07:00

test_vattn_segplan_mi35x.py

[AMD][Bugfix] Fix vattn_asm HIP error 709 under CUDA graph capture on ROCm 10 (#39513 )

2026-09-17 01:06:04 -07:00

test_wan22_fp8_mla.py

[AMD] Fix the diffusion perf fixture lookup (#38686 )

2026-09-10 00:07:08 -07:00

test_zimage_turbo.py

[AMD] Fix the diffusion perf fixture lookup (#38686 )

2026-09-10 00:07:08 -07:00