| .. |
|
apps
|
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)
|
2025-06-20 03:01:10 +08:00 |
|
auto_deploy
|
[#6120][feat] AutoDeploy: flexible args for sequence interface + AD multi-modal input processor + llama4 VLM example (#7221)
|
2025-09-05 22:10:48 -04:00 |
|
bindings/executor
|
|
|
|
cpp/executor
|
[TRTLLM-7030][fix] Refactor the example doc of dist-serving (#6766)
|
2025-08-13 17:39:27 +08:00 |
|
cpp_library
|
|
|
|
disaggregated
|
[None] [feat] Use numa to bind CPU (#7304)
|
2025-08-28 06:27:11 -04:00 |
|
dora
|
|
|
|
draft_target_model
|
Fix: draft target README and set exclude_input_in_output to False (#4882)
|
2025-06-03 23:45:02 -07:00 |
|
eagle
|
doc: remove the outdated features which marked as Experimental (#5995)
|
2025-08-06 22:01:42 -04:00 |
|
infinitebench
|
|
|
|
language_adapter
|
|
|
|
llm-api
|
[TRTLLM-5059][feat] Enable KV-cache reuse and add E2E tests for llava-next (#7349)
|
2025-09-09 14:51:36 -04:00 |
|
llm-eval/lm-eval-harness
|
chore: update doc by replacing use_cuda_graph with cuda_graph_config (#5680)
|
2025-07-04 15:39:15 +09:00 |
|
lookahead
|
|
|
|
medusa
|
|
|
|
models
|
[https://nvbugs/5453709][fix] Remove transformers version limit in Qwen2VL (#7152)
|
2025-09-09 10:38:20 +08:00 |
|
ngram
|
[chore] Clean up quickstart_advanced.py (#6021)
|
2025-07-21 15:00:59 -04:00 |
|
openai_triton
|
|
|
|
python_plugin
|
|
|
|
quantization
|
[#6530][fix] Fix script when using calibration tensors from modelopt (#6803)
|
2025-08-12 20:41:10 -07:00 |
|
redrafter
|
ReDrafter support for Qwen (#4875)
|
2025-06-28 02:33:10 +08:00 |
|
sample_weight_stripping
|
doc: remove the outdated features which marked as Experimental (#5995)
|
2025-08-06 22:01:42 -04:00 |
|
scaffolding
|
[#3325][feat] Add MCTS and TOT tree-based inference controllers to Scaffolding (#7490)
|
2025-09-04 19:46:49 -07:00 |
|
serve
|
[None][chore] Enhance trtllm-serve example test (#6604)
|
2025-08-06 20:30:35 +08:00 |
|
trtllm-eval
|
test: Add LLGuidance test and refine guided decoding (#5348)
|
2025-06-25 14:12:56 +08:00 |
|
wide_ep
|
[TRTLLM-5930][doc] 1.0 Documentation. (#6696)
|
2025-09-09 12:16:03 +08:00 |
|
constraints.txt
|
[None][infra] Bump version to 1.1.0rc5 (#7668)
|
2025-09-10 16:06:54 +08:00 |
|
eval_long_context.py
|
|
|
|
generate_checkpoint_config.py
|
|
|
|
generate_xgrammar_tokenizer_info.py
|
|
|
|
hf_lora_convert.py
|
|
|
|
mmlu.py
|
feat: run mmlu and summarize without engine_dir. (#4056)
|
2025-05-05 19:35:07 +08:00 |
|
run.py
|
[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)
|
2025-07-25 18:10:40 -04:00 |
|
summarize.py
|
[refactor] Unify name of NGram speculative decoding (#5937)
|
2025-07-19 12:59:57 +08:00 |
|
utils.py
|
[refactor] Unify name of NGram speculative decoding (#5937)
|
2025-07-19 12:59:57 +08:00 |
