sglang

configs

…

cpu

Add CPU optimized kernels for topk and rope fusions (#6456 )

2025-06-02 17:37:34 -07:00

models

support qwen3 emebedding (#6990 )

2025-06-09 01:32:49 -07:00

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

…

experiment_runner.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

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

chore: upgrade flashinfer v0.2.6.post1 jit (#6958 )

2025-06-09 09:22:39 -07:00

test_abort.py

…

test_awq.py

…

test_bench_one_batch.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_bench_serving.py

chore: upgrade flashinfer v0.2.6.post1 jit (#6958 )

2025-06-09 09:22:39 -07:00

test_block_int8.py

…

test_bnb.py

Implement Siglip Vision model, and support BNB quantization for gemma3-mm (#5339 )

2025-05-20 23:53:46 -07:00

test_cache_report.py

…

test_chunked_prefill.py

…

test_create_kvindices.py

…

test_custom_allreduce.py

…

test_data_parallelism.py

…

test_deepep_internode.py

Add DeepEP to CI PR Test (#5655 )

2025-05-06 17:36:03 -07:00

test_deepep_intranode.py

Add DeepEP to CI PR Test (#5655 )

2025-05-06 17:36:03 -07:00

test_deepep_low_latency.py

Add DeepEP to CI PR Test (#5655 )

2025-05-06 17:36:03 -07:00

test_disaggregation_different_tp.py

[CI] Fix setup of disaggregation with different tp (#6706 )

2025-05-28 11:17:27 -07:00

test_disaggregation.py

refactor qwen moe code, use communicator to support tp+dp (#6581 )

2025-05-25 23:01:10 -07:00

test_double_sparsity.py

…

test_dp_attention.py

…

test_eagle_infer.py

Fix draft extend ut stability with flush cache (#6979 )

2025-06-08 17:09:32 -07:00

test_ebnf_constrained.py

…

test_embedding_openai_server.py

…

test_enable_thinking.py

…

test_eplb.py

Support layerwise rebalancing experts (#6851 )

2025-06-05 00:05:52 -07:00

test_eval_accuracy_large.py

Fix GPU OOM (#6564 )

2025-05-24 16:38:39 -07:00

test_eval_fp8_accuracy.py

…

test_expert_distribution.py

Support gathering expert distribution details (#6665 )

2025-05-27 15:32:59 -07:00

test_expert_location_updater.py

Support dynamically rebalancing experts using EPLB (#6469 )

2025-05-21 23:13:21 -07:00

test_fa3.py

Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201 )

2025-05-12 00:17:33 -07:00

test_fim_completion.py

Add retry for flaky tests in CI (#4755 )

2025-03-25 16:53:12 -07:00

test_flashmla.py

[Feat] Support FlashMLA backend with MTP and FP8 KV cache (#6109 )

2025-05-15 00:48:09 -07:00

test_fp8_kernel.py

…

test_fp8_kvcache.py

…

test_full_deepseek_v3.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_function_call_parser.py

feat(tool call): Enhance Llama32Detector for improved JSON parsing in non-stream (#6784 )

2025-05-30 17:05:17 -07:00

test_fused_moe.py

…

test_get_weights_by_name.py

…

test_gguf.py

…

test_gptqmodel_dynamic.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

test_health_check.py

…

test_hicache_mla.py

…

test_hicache_page.py

…

test_hicache.py

…

test_hidden_states.py

…

test_input_embeddings.py

…

test_int8_kernel.py

…

test_io_struct.py

Remove duplicate IO Struct test (#6180 )

2025-05-11 12:57:26 +08:00

test_json_constrained.py

Improve structured outputs: fix race condition, server crash, metrics and style (#6188 )

2025-05-11 08:36:16 -07:00

test_json_mode.py

…

test_kv_events.py

feat: add dp-rank to KV events (#6852 )

2025-06-04 15:29:34 -07:00

test_large_max_new_tokens.py

…

test_local_attn.py

…

test_matched_stop.py

Add retry for flaky tests in CI (#4755 )

2025-03-25 16:53:12 -07:00

test_metrics.py

Improve structured outputs: fix race condition, server crash, metrics and style (#6188 )

2025-05-11 08:36:16 -07:00

test_mla_deepseek_v3.py

Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201 )

2025-05-12 00:17:33 -07:00

test_mla_flashinfer.py

Fix CI and triton moe Configs (#6974 )

2025-06-08 05:06:46 -07:00

test_mla_fp8.py

…

test_mla_int8_deepseek_v3.py

Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201 )

2025-05-12 00:17:33 -07:00

test_mla_tp.py

…

test_mla.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_modelopt_fp8kvcache.py

…

test_modelopt.py

…

test_models_from_modelscope.py

…

test_moe_deepep_eval_accuracy_large.py

Add DeepEP to CI PR Test (#5655 )

2025-05-06 17:36:03 -07:00

test_moe_deepep.py

Support custom DeepEP tuning config (#6257 )

2025-05-17 17:09:42 -07:00

test_moe_ep.py

…

test_moe_eval_accuracy_large.py

…

test_mscclpp.py

support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277 )

2025-06-04 22:11:24 -07:00

test_nightly_gsm8k_eval_amd.py

Update amd nightly models CI. (#6992 )

2025-06-09 10:54:08 -07:00

test_nightly_gsm8k_eval.py

…

test_no_chunked_prefill.py

…

test_no_overlap_scheduler.py

…

test_openai_adapter.py

bugfix(OAI): Fix image_data processing for jinja chat templates (#6877 )

2025-06-05 13:37:01 -07:00

test_openai_function_calling.py

ci: relax test_function_call_required (#6786 )

2025-05-30 19:18:42 -07:00

test_openai_server.py

Decoder-only Scoring API (#6460 )

2025-06-04 14:14:54 -07:00

test_page_size.py

…

test_patch_torch.py

…

test_penalty.py

…

test_pp_single_node.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_pytorch_sampling_backend.py

…

test_radix_attention.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_reasoning_content.py

…

test_regex_constrained.py

…

test_release_memory_occupation.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

test_request_length_validation.py

…

test_retract_decode.py

…

test_sagemaker_server.py

…

test_schedule_policy.py

…

test_score_api.py

Decoder-only Scoring API (#6460 )

2025-06-04 14:14:54 -07:00

test_server_args.py

…

test_session_control.py

Add typo checker in pre-commit (#6179 )

2025-05-11 12:55:00 +08:00

test_skip_tokenizer_init.py

Support precomputed multimodal features for Qwen-VL and Gemma3 models. (#6136 )

2025-05-16 12:26:15 -07:00

test_srt_endpoint.py

Skip the flaky test_stateful_custom_logit_processor (#6251 )

2025-05-12 18:29:41 -07:00

test_srt_engine_with_quant_args.py

Revert "fix some typos" (#6244 )

2025-05-12 12:53:26 -07:00

test_srt_engine.py

chore: upgrade flashinfer v0.2.6.post1 jit (#6958 )

2025-06-09 09:22:39 -07:00

test_tool_choice.py

feat: Add warnings for invalid tool_choice and UTs (#6582 )

2025-05-27 16:53:19 -07:00

test_torch_compile_moe.py

Fix throughput threshold for amd ci test (#6414 )

2025-05-19 14:17:41 -07:00

test_torch_compile.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_torch_native_attention_backend.py

…

test_torch_tp.py

…

test_torchao.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

test_triton_attention_backend.py

…

test_triton_attention_kernels.py

Revert "fix some typos" (#6244 )

2025-05-12 12:53:26 -07:00

test_triton_attention_rocm_mla.py

…

test_triton_moe_channel_fp8_kernel.py

…

test_triton_moe_wna16.py

…

test_triton_sliding_window.py

Fix triton sliding window test case (#6981 )

2025-06-08 17:20:46 -07:00

test_two_batch_overlap.py

qwen3moe support two batch overlap (#6598 )

2025-05-25 23:08:16 -07:00

test_update_weights_from_disk.py

…

test_update_weights_from_distributed.py

[fix][RL] Remove the incorrect barrier in init_weights_update_group (#5914 )

2025-05-14 19:15:21 -07:00

test_update_weights_from_tensor.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

test_verl_engine_2_gpu.py

[CI] update verlengine ci to 4-gpu test (#6007 )

2025-05-27 14:32:23 -07:00

test_verl_engine_4_gpu.py

[CI] update verlengine ci to 4-gpu test (#6007 )

2025-05-27 14:32:23 -07:00

test_verl_engine_server.py

…

test_vertex_endpoint.py

…

test_vision_chunked_prefill.py

refactor: minor refactors regarding multimodal processing (#6187 )

2025-05-17 22:53:20 -07:00

test_vision_openai_server_a.py

Improve profiler and integrate profiler in bench_one_batch_server (#6787 )

2025-05-31 15:53:55 -07:00

test_vision_openai_server_b.py

Support LoRA in TestOpenAIVisionServer and fix fused kv_proj loading bug. (#6861 )

2025-06-04 22:08:30 -07:00

test_vision_openai_server_common.py

Support LoRA in TestOpenAIVisionServer and fix fused kv_proj loading bug. (#6861 )

2025-06-04 22:08:30 -07:00

test_vllm_dependency.py

…

test_vlm_accuracy.py

chore: upgrade transformers 4.52.3 (#6575 )

2025-05-25 22:49:58 -07:00

test_vlm_input_format.py

chore: upgrade flashinfer v0.2.6.post1 jit (#6958 )

2025-06-09 09:22:39 -07:00

test_w8a8_quantization.py

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00