Skip to content

[pull] main from NVIDIA:main #1477

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pull merged 2 commits into from
Jul 13, 2026
Merged

[pull] main from NVIDIA:main #1477

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
43dfc81
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Jul 13, 2026
54d484f
[TRTLLM-11558][feat] BREAKING: Acceptance rate based speculation off …
zheyuf Jul 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 13 additions & 9 deletions docs/source/developer-guide/telemetry.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ unset or when the safety sanitizer rejects the runtime value.

### `TorchLlmArgs`

258 captured fields.
261 captured fields.

| Captured key | Annotation | Kind | Converter | Allowed values |
|--------------|------------|------|-----------|----------------|
Expand All @@ -50,6 +50,7 @@ unset or when the safety sanitizer rejects the runtime value.
| `batch_wait_timeout_iters` | `<class 'int'>` | `value` | | |
| `batch_wait_timeout_ms` | `<class 'float'>` | `value` | | |
| `cache_transceiver_config.backend` | `Optional[Literal['DEFAULT', 'UCX', 'NIXL', 'MOONCAKE', 'MPI']]` | `categorical` | | `DEFAULT`, `UCX`, `NIXL`, `MOONCAKE`, `MPI` |
| `cache_transceiver_config.kv_cache_bounce_size_mb` | `<class 'int'>` | `value` | | |
| `cache_transceiver_config.kv_transfer_poll_interval_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
| `cache_transceiver_config.kv_transfer_sender_future_timeout_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
| `cache_transceiver_config.kv_transfer_timeout_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
Expand Down Expand Up @@ -87,6 +88,7 @@ unset or when the safety sanitizer rejects the runtime value.
| `enable_layerwise_nvtx_marker` | `<class 'bool'>` | `value` | | |
| `enable_lm_head_tp_in_adp` | `<class 'bool'>` | `value` | | |
| `enable_lora` | `<class 'bool'>` | `value` | | |
| `enable_low_latency_host_dispatch` | `<class 'bool'>` | `value` | | |
| `enable_min_latency` | `<class 'bool'>` | `value` | | |
| `enable_resource_governor` | `<class 'bool'>` | `value` | | |
| `enable_speculative_beam_history_d2h` | `<class 'bool'>` | `value` | | |
Expand Down Expand Up @@ -154,6 +156,8 @@ unset or when the safety sanitizer rejects the runtime value.
| `moe_config.use_low_precision_moe_combine` | `<class 'bool'>` | `value` | | |
| `moe_expert_parallel_size` | `Optional[int]` | `value` | | |
| `moe_tensor_parallel_size` | `Optional[int]` | `value` | | |
| `multimodal_config.encoder_side_stream_max_ahead` | `<class 'int'>` | `value` | | |
| `multimodal_config.video_pruning_rate` | `Optional[float]` | `value` | | |
| `mx_config.preshard_strategy` | `<class 'str'>` | `categorical` | allowlist | `per_module` |
| `mx_config.server_query_timeout_s` | `Optional[Annotated[int, Ge(ge=0)]]` | `value` | | |
| `num_postprocess_workers` | `<class 'int'>` | `value` | | |
Expand Down Expand Up @@ -230,8 +234,8 @@ unset or when the safety sanitizer rejects the runtime value.
| `sparse_attention_config.use_cute_dsl_paged_mqa_logits` | `<class 'bool'>` | `value` | | |
| `sparse_attention_config.use_cute_dsl_topk` | `<class 'bool'>` | `value` | | |
| `sparse_attention_config.window_size` | `<class 'int'>` | `value` | | |
| `speculative_config.acceptance_length_threshold` | `Optional[Annotated[float, Ge(ge=0)]]` | `value` | | |
| `speculative_config.acceptance_window` | `Optional[Annotated[int, Ge(ge=0)]]` | `value` | | |
| `speculative_config.acceptance_rate_threshold` | `Optional[float]` | `value` | | |
| `speculative_config.acceptance_rate_window_size` | `Optional[Annotated[int, Ge(ge=0)]]` | `value` | | |
| `speculative_config.allow_advanced_sampling` | `<class 'bool'>` | `value` | | |
| `speculative_config.begin_thinking_phase_token` | `<class 'int'>` | `value` | | |
| `speculative_config.decoding_type` | `Literal['AUTO']` | `categorical` | | `AUTO`, `DFlash`, `Draft_Target`, `Eagle3`, `Eagle`, `Lookahead`, `MTP`, `Medusa`, `NGram`, `PARD`, `SA`, `SaveState`, `User_Provided` |
Expand Down Expand Up @@ -288,11 +292,10 @@ unset or when the safety sanitizer rejects the runtime value.
| `use_cute_dsl_bf16_gemm` | `<class 'bool'>` | `value` | | |
| `use_cute_dsl_blockscaling_bmm` | `<class 'bool'>` | `value` | | |
| `use_cute_dsl_blockscaling_mm` | `<class 'bool'>` | `value` | | |
| `video_pruning_rate` | `Optional[float]` | `value` | | |

### `TrtLlmArgs`

279 captured fields.
280 captured fields.

| Captured key | Annotation | Kind | Converter | Allowed values |
|--------------|------------|------|-----------|----------------|
Expand Down Expand Up @@ -368,6 +371,7 @@ unset or when the safety sanitizer rejects the runtime value.
| `build_config.weight_sparsity` | `<class 'bool'>` | `value` | | |
| `build_config.weight_streaming` | `<class 'bool'>` | `value` | | |
| `cache_transceiver_config.backend` | `Optional[Literal['DEFAULT', 'UCX', 'NIXL', 'MOONCAKE', 'MPI']]` | `categorical` | | `DEFAULT`, `UCX`, `NIXL`, `MOONCAKE`, `MPI` |
| `cache_transceiver_config.kv_cache_bounce_size_mb` | `<class 'int'>` | `value` | | |
| `cache_transceiver_config.kv_transfer_poll_interval_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
| `cache_transceiver_config.kv_transfer_sender_future_timeout_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
| `cache_transceiver_config.kv_transfer_timeout_ms` | `Optional[Annotated[int, Gt(gt=0)]]` | `value` | | |
Expand Down Expand Up @@ -480,11 +484,11 @@ unset or when the safety sanitizer rejects the runtime value.
| `quant_config.clamp_val` | `Optional[List[float]]` | `value` | | |
| `quant_config.group_size` | `Optional[int]` | `value` | | |
| `quant_config.has_zero_point` | `<class 'bool'>` | `value` | | |
| `quant_config.kv_cache_quant_algo` | `Optional[tensorrt_llm.quantization.mode.QuantAlgo]` | `categorical` | | `W8A16`, `W4A16`, `W4A16_AWQ`, `W4A8_AWQ`, `W8A16_GPTQ`, `W4A16_GPTQ`, `W8A8_SQ_PER_CHANNEL`, `W8A8_SQ_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN`, `W4A8_QSERVE_PER_GROUP`, `W4A8_QSERVE_PER_CHANNEL`, `FP8`, `FP8_PER_CHANNEL_PER_TOKEN`, `FP8_BLOCK_SCALES`, `INT8`, `MIXED_PRECISION`, `NVFP4`, `W4A8_NVFP4_FP8`, `W4A8_MXFP4_FP8`, `W4A8_MXFP4_MXFP8`, `W4A16_MXFP4`, `MXFP8`, `NVFP4_AWQ`, `NVFP4_ARC`, `NO_QUANT` |
| `quant_config.kv_cache_quant_algo` | `Optional[tensorrt_llm.quantization.mode.QuantAlgo]` | `categorical` | | `W8A16`, `W4A16`, `W4A16_AWQ`, `W4A8_AWQ`, `W8A16_GPTQ`, `W4A16_GPTQ`, `W8A8_SQ_PER_CHANNEL`, `W8A8_SQ_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN`, `W4A8_QSERVE_PER_GROUP`, `W4A8_QSERVE_PER_CHANNEL`, `FP8`, `FP8_PER_CHANNEL_PER_TOKEN`, `FP8_BLOCK_SCALES`, `INT8`, `MIXED_PRECISION`, `NVFP4`, `W4A8_NVFP4_FP8`, `W4A8_MXFP4_FP8`, `W4A8_MXFP4_MXFP8`, `W4A16_MXFP4`, `MXFP8`, `W4A16_NVFP4`, `NVFP4_AWQ`, `NVFP4_ARC`, `NO_QUANT` |
| `quant_config.mamba_ssm_philox_rounds` | `<class 'int'>` | `value` | | |
| `quant_config.mamba_ssm_stochastic_rounding` | `<class 'bool'>` | `value` | | |
| `quant_config.pre_quant_scale` | `<class 'bool'>` | `value` | | |
| `quant_config.quant_algo` | `Optional[tensorrt_llm.quantization.mode.QuantAlgo]` | `categorical` | | `W8A16`, `W4A16`, `W4A16_AWQ`, `W4A8_AWQ`, `W8A16_GPTQ`, `W4A16_GPTQ`, `W8A8_SQ_PER_CHANNEL`, `W8A8_SQ_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN`, `W4A8_QSERVE_PER_GROUP`, `W4A8_QSERVE_PER_CHANNEL`, `FP8`, `FP8_PER_CHANNEL_PER_TOKEN`, `FP8_BLOCK_SCALES`, `INT8`, `MIXED_PRECISION`, `NVFP4`, `W4A8_NVFP4_FP8`, `W4A8_MXFP4_FP8`, `W4A8_MXFP4_MXFP8`, `W4A16_MXFP4`, `MXFP8`, `NVFP4_AWQ`, `NVFP4_ARC`, `NO_QUANT` |
| `quant_config.quant_algo` | `Optional[tensorrt_llm.quantization.mode.QuantAlgo]` | `categorical` | | `W8A16`, `W4A16`, `W4A16_AWQ`, `W4A8_AWQ`, `W8A16_GPTQ`, `W4A16_GPTQ`, `W8A8_SQ_PER_CHANNEL`, `W8A8_SQ_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN`, `W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN`, `W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN`, `W4A8_QSERVE_PER_GROUP`, `W4A8_QSERVE_PER_CHANNEL`, `FP8`, `FP8_PER_CHANNEL_PER_TOKEN`, `FP8_BLOCK_SCALES`, `INT8`, `MIXED_PRECISION`, `NVFP4`, `W4A8_NVFP4_FP8`, `W4A8_MXFP4_FP8`, `W4A8_MXFP4_MXFP8`, `W4A16_MXFP4`, `MXFP8`, `W4A16_NVFP4`, `NVFP4_AWQ`, `NVFP4_ARC`, `NO_QUANT` |
| `quant_config.smoothquant_val` | `<class 'float'>` | `value` | | |
| `quant_config.use_meta_recipe` | `<class 'bool'>` | `value` | | |
| `reasoning_parser` | `Optional[str]` | `categorical` | allowlist | `auto`, `deepseek-r1`, `laguna`, `qwen3`, `qwen3_5`, `minimax_m2`, `minimax_m2_append_think`, `nano-v3`, `gemma4`, `kimi_k2`, `kimi_k25` |
Expand Down Expand Up @@ -528,8 +532,8 @@ unset or when the safety sanitizer rejects the runtime value.
| `sparse_attention_config.use_cute_dsl_paged_mqa_logits` | `<class 'bool'>` | `value` | | |
| `sparse_attention_config.use_cute_dsl_topk` | `<class 'bool'>` | `value` | | |
| `sparse_attention_config.window_size` | `<class 'int'>` | `value` | | |
| `speculative_config.acceptance_length_threshold` | `Optional[Annotated[float, Ge(ge=0)]]` | `value` | | |
| `speculative_config.acceptance_window` | `Optional[Annotated[int, Ge(ge=0)]]` | `value` | | |
| `speculative_config.acceptance_rate_threshold` | `Optional[float]` | `value` | | |
| `speculative_config.acceptance_rate_window_size` | `Optional[Annotated[int, Ge(ge=0)]]` | `value` | | |
| `speculative_config.allow_advanced_sampling` | `<class 'bool'>` | `value` | | |
| `speculative_config.begin_thinking_phase_token` | `<class 'int'>` | `value` | | |
| `speculative_config.decoding_type` | `Literal['AUTO']` | `categorical` | | `AUTO`, `DFlash`, `Draft_Target`, `Eagle3`, `Eagle`, `Lookahead`, `MTP`, `Medusa`, `NGram`, `PARD`, `SA`, `SaveState`, `User_Provided` |
Expand Down
8 changes: 4 additions & 4 deletions security_scanning/examples/auto_deploy/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions security_scanning/examples/llm-eval/lm-eval-harness/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

24 changes: 12 additions & 12 deletions security_scanning/examples/ray_orchestrator/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions security_scanning/examples/serve/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions security_scanning/examples/trtllm-eval/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions security_scanning/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{
"commit_hash": "770ebc5db5c9c1486b8792928fdebf35de73eff3",
"timestamp": "2026-07-13T02:48:18Z"
"commit_hash": "e8321d20974ec61976c037d4a9f3e57ffbd73b80",
"timestamp": "2026-07-13T19:34:01Z"
}
8 changes: 4 additions & 4 deletions security_scanning/poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading
Loading