..
_torch
fix: max_num_sequences calculation with overlap scheduling ( #4532 )
2025-06-03 09:31:22 +02:00
auto_parallel
Release 0.20 to main ( #4577 )
2025-05-28 16:25:33 +08:00
bench
Cherry pick feat/llama4 to main ( #4739 )
2025-05-30 05:28:40 +08:00
commands
opt: the perormance for dist-agg streaming generation ( #4214 )
2025-05-31 17:40:32 +08:00
evaluate
Add llama4 disagg accuracy tests ( #4336 )
2025-05-19 21:55:08 +08:00
executor
fix [nvbug5256044]: bench hang due to llmapi ipc ( #4798 )
2025-06-03 10:10:53 +08:00
inputs
fix: Move cv2 import to load_video function ( #4541 )
2025-05-22 17:56:07 +02:00
layers
refactor: use x is None instead of x == None. ( #4244 )
2025-05-15 20:00:04 +08:00
llmapi
[fix] Fix SamplingParams check on n and best_of ( #4655 )
2025-06-01 09:11:55 +08:00
models
[NVBUG 5301980] Fix fp4 gemm padding. ( #4662 )
2025-05-27 11:30:53 +08:00
plugin
Cherry pick feat/llama4 to main ( #4739 )
2025-05-30 05:28:40 +08:00
quantization
[NVBUG 5301980] Fix fp4 gemm padding. ( #4662 )
2025-05-27 11:30:53 +08:00
runtime
fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow. ( #4399 )
2025-05-19 14:25:36 -07:00
scaffolding
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs ( #4603 )
2025-05-28 18:43:04 +08:00
serve
[feat] support sharegpt downloading in benchmark_serving ( #4578 )
2025-05-30 17:27:53 +08:00
tools
feat: Support Mistral Small 3.1 24B VLM in TRT workflow ( #4183 )
2025-05-14 03:47:22 +08:00
__init__.py
chore: Partition LlmArgs into TorchLlmArgs and TrtLlmArgs ( #3823 )
2025-05-22 09:40:56 +08:00
_common.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
_dlpack_utils.py
feat: Add MNNVL MoE A2A support ( #3504 )
2025-04-25 17:29:08 +08:00
_ipc_utils.py
fix: Proper error bubbling for PyExecutor ( #3321 )
2025-04-15 14:49:46 +08:00
_mnnvl_utils.py
fix: Remove real size allocation ( #4396 )
2025-05-18 19:13:22 +08:00
_utils.py
feat: Skip sampler for intermediate pp stages. ( #4514 )
2025-05-26 10:08:51 +08:00
builder.py
chore: remove usernames from comments ( #3291 )
2025-04-05 13:44:28 +08:00
disaggregated_params.py
Update TensorRT-LLM ( #2936 )
2025-03-18 21:25:19 +08:00
functional.py
feat: Low Precision Allreduce for PCIe based GPU ( #4344 )
2025-05-20 06:53:46 +08:00
graph_rewriting.py
Update TensorRT-LLM ( #2755 )
2025-02-11 03:01:00 +00:00
logger.py
perf: Fuse gemm setup function for SM90/SM100 MOE plugin path ( #4146 )
2025-05-21 10:00:36 +08:00
lora_manager.py
add changes for fp8, nemotron-nas, API ( #4180 )
2025-05-18 23:27:25 +08:00
mapping.py
fix: Fix moe_ep_groups/moe_cluster_groups in Mapping. ( #4555 )
2025-05-23 10:41:49 +08:00
module.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
network.py
chore: remove usernames from comments ( #3291 )
2025-04-05 13:44:28 +08:00
parameter.py
fix: https://nvbugs/5234033 enable starcoder trt-flow with transforme… ( #3909 )
2025-05-15 11:16:45 +08:00
profiler.py
test [TRTLLM-4477,TRTLLM-4481]: Accuracy test improvement (Part 3.5): Support GSM8K and GPQA ( #3483 )
2025-04-22 07:38:16 +08:00
prompt_adapter_manager.py
Update TensorRT-LLM ( #2333 )
2024-10-15 15:28:40 +08:00
python_plugin.py
refactor: use x is None instead of x == None. ( #4244 )
2025-05-15 20:00:04 +08:00
sampling_params.py
[fix] Fix SamplingParams check on n and best_of ( #4655 )
2025-06-01 09:11:55 +08:00
top_model_mixin.py
Update TensorRT-LLM ( #2053 )
2024-07-30 21:25:01 +08:00
version.py
chore: bump version to 0.21.0rc0 ( #4465 )
2025-05-20 12:19:50 +08:00
b9263a8e10