Netanel Haber 6ee94c7ac8 Reintroduce with perf fixes: feature: unify new_tokens format sample state to trtllm samper tokens format (#5513) ... 58a8a8f - these changes were previously merged to main here. 6aef149 - the changes were temporarily reverted in main, due to a significant perf regression in models using the TorchSampler (observed by @byshiue). This PR is meant to re-merge these changes along with a fix to prevent the regression. The first commit of this PR is actually just the reverted revert - filter it out of the changes to see previously unmerged changes. Signed-off-by: Netanel Haber <nhaber@nvidia.com>		2025-06-30 11:58:59 -07:00
..
_tensorrt_engine	[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)	2025-06-20 03:01:10 +08:00
_torch	Reintroduce with perf fixes: feature: unify new_tokens format sample state to trtllm samper tokens format (#5513)	2025-06-30 11:58:59 -07:00
auto_parallel	[TRTLLM-4971]: Use safe deserialization in ParallelConfig (#4630)	2025-06-27 09:58:41 +08:00
bench	chore: remove cuda_graph_ prefix from cuda_graph_config filed members. (#5585)	2025-06-30 12:23:14 -04:00
commands	[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)	2025-06-20 03:01:10 +08:00
evaluate	test: Add LLGuidance test and refine guided decoding (#5348)	2025-06-25 14:12:56 +08:00
executor	[TRTLLM-6104] feat: add request_perf_metrics to LLMAPI (#5497)	2025-06-27 17:03:05 +02:00
inputs	feat: Basic skeleton for Gemma3 VLM (#5108)	2025-06-13 17:27:04 +08:00
layers	refactoring: port customized kernels with public cutlass version (#5027)	2025-06-13 16:19:31 +08:00
llmapi	chore: remove cuda_graph_ prefix from cuda_graph_config filed members. (#5585)	2025-06-30 12:23:14 -04:00
models	ReDrafter support for Qwen (#4875)	2025-06-28 02:33:10 +08:00
plugin	feat: Add support for fp8 rowwise quantization (#4876)	2025-06-14 06:37:48 -07:00
quantization	perf: Optimize swizzle_sf, unswizzle_sf, reswizzle_sf (#5318)	2025-06-26 14:03:56 +08:00
runtime	chore: Mass integration of release/0.20 (#5082)	2025-06-17 14:32:02 +03:00
scaffolding	[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)	2025-06-20 03:01:10 +08:00
serve	[TRTLLM-5831][feat] Add LoRA support for pytorch backend in trtllm-serve (#5376)	2025-06-29 12:46:30 +00:00
tools	chore: Mass integration of release/0.20 (#4898)	2025-06-08 23:26:26 +08:00
__init__.py	perf: Optimize swizzle_sf, unswizzle_sf, reswizzle_sf (#5318)	2025-06-26 14:03:56 +08:00
_common.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
_dlpack_utils.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
_ipc_utils.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
_mnnvl_utils.py	[TRTLLM-5331] perf: Replace allgaher with AllToAllPrepare (#5570)	2025-06-30 13:06:09 +08:00
_utils.py	[feat] Add llm args to tune python gc threshold (#5141)	2025-06-16 17:45:22 +08:00
builder.py	fix: build_config in TorchLlmArgs and avoid arbitrary args (#4972)	2025-06-15 17:51:56 -07:00
disaggregated_params.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
functional.py	Feat/ds r1 min latency opt round3, add router gemm, fused a gemm, PDL (#4560)	2025-06-14 17:36:22 +08:00
graph_rewriting.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
logger.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
lora_manager.py	[TRTLLM-5921][feat] Prevent serialization of entire LoRA adapters in each request (#5080)	2025-06-26 08:15:06 +03:00
mapping.py	fix: Mapping rank boundary check bug (#4935)	2025-06-27 07:27:59 +08:00
math_utils.py	perf: Optimize swizzle_sf, unswizzle_sf, reswizzle_sf (#5318)	2025-06-26 14:03:56 +08:00
module.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +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	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
prompt_adapter_manager.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
python_plugin.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
sampling_params.py	test: Add LLGuidance test and refine guided decoding (#5348)	2025-06-25 14:12:56 +08:00
serialization.py	[TRTLLM-4971]: Use safe deserialization in ParallelConfig (#4630)	2025-06-27 09:58:41 +08:00
top_model_mixin.py	linting(python): Enable ruff on more files (wave 1/N) (#5140)	2025-06-14 19:19:34 +08:00
version.py	chore: bump version to 1.0.0rc1 (#5460)	2025-06-25 16:21:34 +08:00