Commit 05316d3
1 parent 9bd15f1 commit 05316d3
File tree
1,024 files changed
+2084834
-868880
lines changed- benchmarks
- cpp
- utils
- python
- suite/tensorrt_llm_bench
- benchmarkers
- utils
- cpp
- cmake/utils
- include/tensorrt_llm
- batch_manager
- common
- executor
- kernels
- layers
- runtime
- utils
- micro_benchmarks
- tensorrt_llm
- batch_manager
- aarch64-linux-gnu
- x86_64-linux-gnu
- x86_64-windows-msvc
- common
- cutlass_extensions/include/cutlass_extensions
- gemm
- collective
- builders
- kernel
- threadblock
- transform/threadblock
- executor
- aarch64-linux-gnu
- x86_64-linux-gnu
- x86_64-windows-msvc
- kernels
- beamSearchKernels
- contextFusedMultiHeadAttention
- cubin
- cutlass_kernels
- fpA_intB_gemm
- launchers
- fused_gated_gemm
- int8_gemm
- moe_gemm
- launchers
- python
- decoderMaskedMultiheadAttention
- cubin
- decoderXQAImplJIT
- nvrtcWrapper
- aarch64-linux-gnu
- include
- x86_64-linux-gnu
- x86_64-windows-msvc
- instantiation
- mixtureOfExperts
- parallelDecoding
- speculativeDecoding
- unfusedAttentionKernels
- weightOnlyBatchedGemv
- layers
- plugins
- api
- bertAttentionPlugin
- common
- cumsumLastDimPlugin
- gemmPlugin
- gemmSwigluPlugin
- gptAttentionCommon
- gptAttentionPlugin
- layernormQuantizationPlugin
- lookupPlugin
- loraPlugin
- lruPlugin
- mambaConv1dPlugin
- mixtureOfExperts
- ncclPlugin
- quantizePerTokenPlugin
- quantizeTensorPlugin
- rmsnormQuantizationPlugin
- selectiveScanPlugin
- smoothQuantGemmPlugin
- weightOnlyGroupwiseQuantMatmulPlugin
- weightOnlyQuantMatmulPlugin
- pybind
- batch_manager
- executor
- runtime
- runtime
- utils
- thop
- tests
- common
- kernels
- allReduce
- fp8Gemm
- fused_gated_gemm
- sampling
- weightOnly
- layers
- resources
- data
- scripts
- runtime
- docker
- common
- docs/source
- advanced
- architecture
- blogs
- installation
- media
- performance
- reference
- examples
- apps
- arctic
- baichuan
- bert
- bindings/executor
- bloom
- chatglm
- cogvlm
- dbrx
- dit
- figs
- enc_dec
- falcon
- gemma
- gpt
- gptj
- gptneox
- grok
- high-level-api
- infinitebench
- internlm
- internlm2
- jais
- llama
- mamba
- medusa
- mixtral
- model_api
- mpt
- multimodal
- nemotron
- openai_triton
- manual_plugin
- plugin_autogen
- opt
- phi
- quantization
- qwen
- qwenvl
- recurrentgemma
- sample_weight_stripping
- skywork
- smaug
- whisper
- distil_whisper
- scripts
- tensorrt_llm
- auto_parallel
- tensor_parallel
- plugin_nodes
- commands
- hlapi
- layers
- models
- cogvlm
- dbrx
- dit
- enc_dec
- gemma
- gpt
- gptneox
- grok
- llama
- mamba
- medusa
- mpt
- opt
- phi
- phi3
- qwen
- recurrentgemma
- plugin
- quantization
- runtime
- tests
- attention
- bindings
- functional
- hlapi
- apps
- model
- model_api
- quantization
- utils
- windows
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
1,024 files changed
+2084834
-868880
lines changed+1-1
Original file line number | Diff line number | Diff line change | |
---|---|---|---|
| |||
6 | 6 |
| |
7 | 7 |
| |
8 | 8 |
| |
| 9 | + | |
9 | 10 |
| |
10 | 11 |
| |
11 |
| - | |
12 | 12 |
| |
13 | 13 |
| |
14 | 14 |
| |
|
Original file line number | Diff line number | Diff line change | |
---|---|---|---|
| |||
46 | 46 |
| |
47 | 47 |
| |
48 | 48 |
| |
49 |
| - | |
| 49 | + | |
50 | 50 |
|
0 commit comments