kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 15:55:08 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4debf153d8
TensorRT-LLMs/tests/unittest/llmapi/apps
History
William Zhang 4debf153d8
[#11170][fix] Fix for mm placeholder counts (#11461) 
* Why?

As reported by #11170, when a single request contains multiple
messages, and only a subset of those messages include multimodal data,
the previous logic incorrectly adds placeholder tokens to subsequent
messages that do not contain such data.

* What?

This commit fixes this issue, and adds unit tests that would have
caught this.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
2026-02-14 09:12:03 +08:00
..
_attach_multimodal_embeddings_patch [TRTLLM-9522][feat] support image_embeds in OpenAI API (#9715) 2026-01-14 10:31:03 +01:00
__init__.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
_test_disagg_serving_multi_nodes_service_discovery.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
_test_disagg_serving_multi_nodes.py [TRTLLM-9840][test] switch ucx backend to default backend (#10101) 2025-12-18 18:54:15 -08:00
_test_llm_chat.py Add thread leak check and fix thread/memory leak issues. (#3270) 2025-04-08 19:03:18 +08:00
_test_llm_server.py Add thread leak check and fix thread/memory leak issues. (#3270) 2025-04-08 19:03:18 +08:00
_test_openai_cache_salt.py [TRTLLM-7398][feat] Support KV cache salting for secure KV cache reuse (#7106) 2025-09-06 17:58:32 -04:00
_test_openai_chat_guided_decoding.py [https://nvbugs/5837281][fix] Fix trtllm-serve guided decoding test (#11101) 2026-01-30 16:59:55 +08:00
_test_openai_chat_harmony.py [#10614][fix] gpt_oss first iteration streaming in trtllm-serve (#10808) 2026-01-26 20:53:11 +08:00
_test_openai_chat_multimodal.py [TRTLLM-9522][feat] support image_embeds in OpenAI API (#9715) 2026-01-14 10:31:03 +01:00
_test_openai_chat.py [TRTLLM-8598][feat] enable n > 1 in OpenAI API with PyTorch backend (#8951) 2025-11-07 17:47:35 -08:00
_test_openai_completions.py [TRTLLM-10388][feat] Support logprobs for Completions API (#10809) 2026-01-22 21:25:24 +08:00
_test_openai_consistent_chat.py [TRTLLM-8682][chore] Remove auto_parallel module (#8329) 2025-10-22 20:53:08 -04:00
_test_openai_lora.py [https://nvbugs/5390853][fix] Fix _test_openai_lora.py - disable cuda graph (#6965) 2025-08-17 16:56:16 +03:00
_test_openai_metrics.py [TRTLLM-8274][feat] Check if executor is shutdown in /health entrypoint (#9057) 2025-12-04 13:49:40 +08:00
_test_openai_misc.py [None][fix] make health_generate work with beam search (#11097) 2026-02-04 09:46:19 +01:00
_test_openai_mmencoder.py [TRTLLM-9522][feat] support image_embeds in OpenAI API (#9715) 2026-01-14 10:31:03 +01:00
_test_openai_multi_chat.py [TRTLLM-8682][chore] Remove auto_parallel module (#8329) 2025-10-22 20:53:08 -04:00
_test_openai_multi_gpu.py [BREAKING CHANGE]: change default backend to PyTorch in trtllm-serve (#5717) 2025-07-21 21:09:43 +08:00
_test_openai_multi_nodes.py [BREAKING CHANGE]: change default backend to PyTorch in trtllm-serve (#5717) 2025-07-21 21:09:43 +08:00
_test_openai_perf_metrics.py [TRTLLM-6549][feat] add perf metrics endpoint to openai server and openai disagg server (#6985) 2025-08-26 15:34:44 +08:00
_test_openai_prometheus.py [None][feat] Add trtllm_ prefix for exposed metrics (#8845) 2025-11-06 15:27:18 +08:00
_test_openai_reasoning.py [None][feat] Support Qwen3 reasoning parser (#8000) 2025-10-21 14:08:39 +08:00
_test_openai_responses_entrypoint.py [TRTLLM-8462][feat] Support GET/DELETE v1/responses/{response_id} (#9937) 2026-01-13 03:57:14 -05:00
_test_openai_responses.py [https://nvbugs/5804146][fix] Enable responses tests and remove ds to… (#10925) 2026-02-09 23:53:40 +08:00
_test_openai_tool_call.py [TRTLLM-8214][feat] Support Qwen3 tool parser (#8216) 2025-10-29 15:48:29 +08:00
_test_trtllm_serve_benchmark.py [TRTLLM-7070][feat] add gpt-oss chunked prefill tests (#7779) 2025-09-22 00:12:43 -07:00
_test_trtllm_serve_duplicated_args.py chore: update trtllm-serve usage doc by removing backend parameter when it use torch as backend. (#6419) 2025-07-30 11:11:06 -04:00
_test_trtllm_serve_example.py [https://nvbugs/5747938][fix] Use local tokenizer (#10230) 2025-12-26 22:08:10 +08:00
_test_trtllm_serve_lora.py [5830][feat] Improve LoRA cache memory control (#6220) 2025-07-31 09:26:38 +03:00
_test_trtllm_serve_multimodal_benchmark.py [https://nvbugs/5494698][fix] skip gemma3 27b on blackwell (#7505) 2025-09-10 21:09:27 +08:00
_test_trtllm_serve_multimodal_example.py [https://nvbugs/5747920][fix] Fix multimodal serve test (#11296) 2026-02-05 15:12:53 +09:00
_test_trtllm_serve_top_logprobs.py [TRTLLM-10388][feat] Support logprobs for Completions API (#10809) 2026-01-22 21:25:24 +08:00
openai_server.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
README.md [TRTLLM-8214][feat] Support Qwen3 tool parser (#8216) 2025-10-29 15:48:29 +08:00
test_chat_utils.py [#11170][fix] Fix for mm placeholder counts (#11461) 2026-02-14 09:12:03 +08:00
test_disagg_serving_perf_metrics.py [https://nvbugs/5726066][fix] fix auto-scaling related failures (#9845) 2025-12-18 16:37:48 -05:00
test_harmony_channel_validation.py [#10614][fix] gpt_oss first iteration streaming in trtllm-serve (#10808) 2026-01-26 20:53:11 +08:00
test_tool_parsers.py [TRTLLM-9677][feat] Support DeepSeek-V3.2 tool parser (#10126) 2025-12-23 08:46:47 +08:00
utils.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00

README.md

This directory contains the end-to-end tests for trtllm-serve.

These tests are triggered in the test_e2e.py.