| .. |
|
auto_deploy
|
[AutoDeploy] merge feat/ad-2025-07-22 (#6520)
|
2025-08-01 08:51:08 -07:00 |
|
compilation
|
[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)
|
2025-05-09 11:04:01 +08:00 |
|
debugger
|
Fix: fix nvbug 5356427 (#5464)
|
2025-06-25 22:24:26 +08:00 |
|
modeling
|
[None][chore] Update Gemma3 closeness check to mitigate flakiness (#6591)
|
2025-08-04 10:10:58 -04:00 |
|
modules
|
Deepseek R1 FP8 Support on Blackwell (#6486)
|
2025-08-01 10:26:28 +08:00 |
|
multi_gpu
|
[fix][nvbugs/5399355] Fix Lamport buffer clear issue for MNNVL TwoShot Allreduce and add FP16 support. (#6237)
|
2025-07-25 08:01:40 +08:00 |
|
multi_gpu_modeling
|
[TRTLLM-5530][BREAKING CHANGE] refactor: unify KvCacheConfig in LLM class for pytorch backend (#5752)
|
2025-07-16 16:42:59 +08:00 |
|
multimodal
|
[TRTLLM-6654][feat] Add support for external multimodal embeddings (#6263)
|
2025-07-30 10:00:15 -04:00 |
|
speculative
|
[TRTLLM-6392][feat] Support turning on/off spec decoding dynamically (#6363)
|
2025-07-31 15:31:39 -04:00 |
|
thop
|
Deepseek R1 FP8 Support on Blackwell (#6486)
|
2025-08-01 10:26:28 +08:00 |
|
helpers.py
|
Deepseek R1 FP8 Support on Blackwell (#6486)
|
2025-08-01 10:26:28 +08:00 |
|
pattern_watcher.py
|
[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)
|
2025-05-09 11:04:01 +08:00 |
|
test_attention_mla.py
|
fix mla test (#5240)
|
2025-06-17 15:26:25 +08:00 |
|
test_attention_no_cache.py
|
refactor(test): remove random context sequence lengths and set seed for reproducibility in attention tests (#3919)
|
2025-04-29 10:08:04 +08:00 |
|
test_attention.py
|
reduce num layers in attention test (#3509)
|
2025-04-14 12:43:59 +08:00 |
|
test_autotuner.py
|
feat: Enhance AutoTuner inference path and code readability (#4466)
|
2025-06-04 10:53:11 +08:00 |
|
test_beam_search.py
|
[TRTLLM-5061] chore: add status tags to LLM API reference (#5707)
|
2025-07-28 15:57:07 +08:00 |
|
test_best_of_n.py
|
[TRTLLM-5271][feat] best_of/n for pytorch workflow (#5997)
|
2025-08-04 14:08:06 +02:00 |
|
test_custom_ops.py
|
[TRTLLM-4279] fix: Add a protection test for checking trtllm custom ops (#6515)
|
2025-08-01 15:59:09 +08:00 |
|
test_executor_request_queue.py
|
[TRTLLM-5271][feat] best_of/n for pytorch workflow (#5997)
|
2025-08-04 14:08:06 +02:00 |
|
test_flashinfer_attention.py
|
Add thread leak check and fix thread/memory leak issues. (#3270)
|
2025-04-08 19:03:18 +08:00 |
|
test_flashinfer_star_attn.py
|
Add thread leak check and fix thread/memory leak issues. (#3270)
|
2025-04-08 19:03:18 +08:00 |
|
test_fp8_per_tensor_scale_tllmg_gemm.py
|
fix: [5328141] increase tolerance for test_fp8_block_scale_gemm (#5849)
|
2025-07-22 12:48:00 +08:00 |
|
test_group_rmn_norm.py
|
feat: Add heuristic for GroupRMSNorm kernel selection. (#4047)
|
2025-05-13 08:52:53 +08:00 |
|
test_mnnvl_memory.py
|
feat: Add MNNVL MoE A2A support (#3504)
|
2025-04-25 17:29:08 +08:00 |
|
test_overlap_scheduler_input.json
|
refactor: Unify request order in TRT and PyTorch workflow (#4096)
|
2025-05-20 18:49:27 +02:00 |
|
test_overlap_scheduler.py
|
[ci] parallelize torch unittests (#5714)
|
2025-07-09 11:05:57 +03:00 |
|
test_pytorch_model_engine.py
|
[TRTLLM-5493] Add core infrastructure to enable loading of custom checkpoint formats (#5372)
|
2025-07-17 00:50:30 +08:00 |
|
test_resource_manager.py
|
fix: adjust window sizes of VSWA at torch backend (#5880)
|
2025-07-15 17:41:54 +08:00 |
|
test_return_logits.py
|
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)
|
2025-06-20 03:01:10 +08:00 |
|
test_share_tensor.py
|
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes (#5396)
|
2025-07-10 05:12:53 +09:00 |
|
test_trtllm_sampler.py
|
[fix] Add detokenization-based stop word logic to LLM API (#5948)
|
2025-07-29 10:16:59 -07:00 |
|
test_vanilla_attention.py
|
Add thread leak check and fix thread/memory leak issues. (#3270)
|
2025-04-08 19:03:18 +08:00 |
|
test_virtual_memory.py
|
[TRTLLM-4406][feat] LLM sleep & wakeup Part 1: virtual device memory (#5034)
|
2025-08-04 13:51:01 +08:00 |
