ShaneGZhu 2d8338f9e4 [Optimization][DeepSeekV3.2]Reducing slot_mapping compute frequency from twice per layer to a single pre-processing step. (#7367)

2026-04-16 19:54:12 +08:00

..

test_deterministic_logger.py

[Feature][BugFix][OP] Enhance Deterministic Inference Mode with Kernel-level Fixes and Batch-invariant BMM (#6610)

2026-03-09 10:27:53 +08:00

test_gpu_model_runner.py

[RL] Add clear_graph_opt_backend for glm4_mtp (#7378)

2026-04-15 19:44:15 +08:00

test_gpu_prompt_logprobs.py

Split enable_mm (#7183)

2026-04-08 11:25:41 +08:00

test_gpu_worker.py

[RL] [KVCache] let cache transfer managers update key prefix after weight update and add unit tests (#7083)

2026-04-02 19:58:41 +08:00

test_logprobs_output.py

[Optimization] support mm prefill batch (#5313)

2025-12-11 22:21:14 +08:00

test_reorder_split_prefill_and_decode.py

[Optimization][DeepSeekV3.2]Reducing slot_mapping compute frequency from twice per layer to a single pre-processing step. (#7367)

2026-04-16 19:54:12 +08:00

test_worker_eplb.py

[CI] Add unittest (#5328)

2025-12-09 19:19:42 +08:00

test_worker_process.py

[RL] [KVCache] let cache transfer managers update key prefix after weight update and add unit tests (#7083)

2026-04-02 19:58:41 +08:00