kanghui0204 6f3922f318 feat: Low Precision Allreduce for PCIe based GPU (#4344) ... This PR adds a customized allreduce to TensorRT-LLM. The new allreduce is used for communication on PCIe-based GPUs via low-precision quantization, which can accelerate the PCIe allreduce process. Signed-off-by: Hui Kang <hkang@nvidia.com> Co-authored-by: Hui Kang <hkang@nvidia.com>		2025-05-20 06:53:46 +08:00
..
_static	[Docs] - Reapply #4220 (#4434)	2025-05-19 22:52:37 +08:00
_templates	Update TensorRT-LLM (#1725)	2024-06-04 20:26:32 +08:00
advanced	feat: Low Precision Allreduce for PCIe based GPU (#4344)	2025-05-20 06:53:46 +08:00
architecture	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00
blogs	refine doc (#4422)	2025-05-19 06:06:22 +08:00
commands	feat: enhance trtllm serve multimodal (#3757)	2025-05-15 16:16:31 -07:00
dev-on-cloud	doc: add doc ahout developent on cloud or runpod (#3194)	2025-04-02 18:10:56 +08:00
examples	doc: refactor trtllm-serve examples and doc (#3187)	2025-04-04 11:40:43 +08:00
installation	[Infra][Docs] - Some clean-up for the CI pipeline and docs (#4419)	2025-05-19 00:07:45 +08:00
llm-api	doc: fix path after examples migration (#3814)	2025-04-24 02:36:45 +08:00
media	L4 added to readme (#3301)	2025-04-06 19:09:28 +08:00
performance	fix: wrong argument name enable_overlap_scheduler (#4433)	2025-05-19 15:02:22 +08:00
python-api	Update TensorRT-LLM (#1492)	2024-04-24 14:44:22 +08:00
reference	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00
torch	Remove dummy forward path (#3669)	2025-04-18 16:17:50 +08:00
conf.py	[Docs] - Reapply #4220 (#4434)	2025-05-19 22:52:37 +08:00
helper.py	doc: refactor trtllm-serve examples and doc (#3187)	2025-04-04 11:40:43 +08:00
index.rst	doc： DS r1 min latency blog (#4386)	2025-05-16 20:20:28 +08:00
key-features.md	Update TensorRT-LLM (#2562)	2024-12-11 00:31:05 -08:00
overview.md	chore: Mass integration of release/0.18 (#3421)	2025-04-16 10:03:29 +08:00
quick-start-guide.md	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00
release-notes.md	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00
torch.md	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00