mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-10 21:13:34 +08:00
5fa6fbd989
Fix AutoTuner warmup request generating. * The current warmup phase creates one request, which is insufficient for the warmup to cover the max_num_tokens. Revise the warmup phase to a batch of requests to cover the max_num_tokens to eliminate potential fallback cases. Refactor AutoTuner API and reduce host overhead. Refine (min, opt, max) values of optimization profile setup for get_valid_tactics to achieve the correct canImplement definition. * Refine cache key assembly process to reduce host overhead and simplify API. * Fix lru_cache usage to reduce host overhead. * Move tuning config initialization as a one-time object in tunable runner to reduce host overhead. Improve tuning config readability. * Use dataclass to define tuning config. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| auto_deploy | ||
| compilation | ||
| modeling | ||
| modules | ||
| multi_gpu | ||
| multi_gpu_modeling | ||
| speculative | ||
| thop | ||
| helpers.py | ||
| pattern_watcher.py | ||
| test_attention_mla.py | ||
| test_attention_no_cache.py | ||
| test_attention.py | ||
| test_autotuner.py | ||
| test_flashinfer_attention.py | ||
| test_flashinfer_star_attn.py | ||
| test_fp8_per_tensor_scale_tllmg_gemm.py | ||
| test_group_rmn_norm.py | ||
| test_mnnvl_memory.py | ||
| test_overlap_scheduler_input.json | ||
| test_overlap_scheduler.py | ||
| test_pytorch_model_engine.py | ||
| test_resource_manager.py | ||
| test_return_logits.py | ||
| test_trtllm_sampler.py | ||
| test_vanilla_attention.py | ||