| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)
|
2025-10-24 13:40:41 -04:00 |
|
config_utils.py
|
[None][chore] Refine qwen3-next implementation. (#8064)
|
2025-09-30 15:05:13 -04:00 |
|
config.py
|
[None][chore] Cherry-pick from (#7598) Make low_precision_combine as a llm arg (#7898)
|
2025-09-28 22:32:33 -04:00 |
|
cuda_graph_runner.py
|
[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)
|
2025-10-21 11:11:04 -04:00 |
|
executor_request_queue.py
|
[TRTLLM-7349][feat] Adding new orchestrator type -- ray (#7520)
|
2025-10-04 08:12:24 +08:00 |
|
finish_reason.py
|
[TRTLLM-5974][feat] Support disaggregated serving in TRTLLM Sampler (#5328)
|
2025-06-25 17:41:36 +02:00 |
|
grammar_matcher.py
|
[TRTLLM-8209][feat] Support new structural tag API (upgrade XGrammar to 0.1.25) (#7893)
|
2025-09-23 09:10:09 +08:00 |
|
guided_decoder.py
|
[None][fix] Disable torch.compile for CapturableGuidedDecoder (#7871)
|
2025-09-22 10:04:30 +08:00 |
|
handle_additional_outputs.py
|
[TRTLLM-4517] [feat] Additional model outputs (#7206)
|
2025-10-13 15:33:18 +02:00 |
|
handle_logits.py
|
[TRTLLM-8031][feat] Add chunked return_generation_logits logic (#7831)
|
2025-10-01 12:47:07 -04:00 |
|
kv_cache_connector.py
|
[None][feat] Support KV Connector with Disagg Prefill Worker (#8246)
|
2025-10-24 11:09:06 -07:00 |
|
kv_cache_transceiver.py
|
[TRTLLM-7078][chore] optimal kvcache transfer for VWSA (#7952)
|
2025-10-24 08:58:16 -04:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
[None][feat] Pass KvCacheRetentionConfig to torch LlmRequest (#8634)
|
2025-10-24 06:44:34 -07:00 |
|
make_decoding_batch_input_output.py
|
feat: Optimize TRTLLM Sampler perf single beam single step (#5550)
|
2025-07-07 15:44:47 +02:00 |
|
mamba_cache_manager.py
|
[TRTLLM-8477][chore] Replace KvCacheConfigCpp with KvCacheConfig inside PyExecutor (#8259)
|
2025-10-13 14:55:36 +08:00 |
|
model_engine.py
|
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)
|
2025-10-24 13:40:41 -04:00 |
|
model_loader.py
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
py_executor_creator.py
|
[None][feat] Support KV Connector with Disagg Prefill Worker (#8246)
|
2025-10-24 11:09:06 -07:00 |
|
py_executor.py
|
[None][feat] Support KV Connector with Disagg Prefill Worker (#8246)
|
2025-10-24 11:09:06 -07:00 |
|
resource_manager.py
|
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)
|
2025-10-24 13:40:41 -04:00 |
|
sampler.py
|
[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)
|
2025-10-21 11:11:04 -04:00 |
|
sampling_utils.py
|
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements (#8398)
|
2025-10-20 11:15:41 +02:00 |
|
scheduler.py
|
[TRTLLM-8483][chore] Refine scheduler_config and peft_cache_config in create_py_executor (#8451)
|
2025-10-22 08:33:48 +08:00 |
|
seq_slot_manager.py
|
[https://nvbugs/5394392][fix] Enlarge scheduler capacity under disagg bs == 1 (#6537)
|
2025-08-15 09:52:06 -07:00 |
