Yanwen LinandHarry Mellor 675ec59aa9 [Bugfix][CPU] Fix basic unit tests failing in CPU platforms (#34677) ...

Signed-off-by: Yanwen Lin <lyw1124278064@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-02-25 08:36:15 +00:00

..

basic_correctness

[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)

2026-02-13 08:11:26 -08:00

benchmarks

…

compile

[ROCm]: Enable customop and rope+kvcache fusion for AITER RoPE (#35180)

2026-02-25 04:36:40 +00:00

config

[Bugfix] Exclude language_model_only key from MM AOT compile hash but include in model one (#34508)

2026-02-13 13:59:00 +00:00

cuda

…

detokenizer

[CI/Build] Remove use of skip_v1 (#34699)

2026-02-18 12:19:11 +08:00

distributed

[AMD][CI] Fix test_custom_allreduce for A100 testgroup (#34735)

2026-02-20 21:33:04 +00:00

engine

…

entrypoints

[Responses][CI] Filter negative token IDs in schema fuzz test to avoid 500 errors (#35231)

2026-02-25 05:52:44 +00:00

evals

[Bugfix] Fix NVFP4 TRTLLM MoE non-gated support; add gsm8k for Nemotron-3-Nano FP8+NVFP4 (#34725)

2026-02-18 09:39:22 -08:00

kernels

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

lora

[Bugfix] Fix lora_ids in FusedMoE LoRA test (#35135)

2026-02-23 21:49:25 -05:00

model_executor

[Perf] Add opt-in SM100 Oink RMSNorm custom-op path (#31828)

2026-02-24 23:01:53 -08:00

models

Remove requirement to use --hf-overrides for DeepseekVLV2ForCausalLM (#35203)

2026-02-24 22:00:06 -08:00

multimodal

[MM] Allow audio chunking for offline LLM (#34628)

2026-02-23 21:04:28 -08:00

plugins

[Misc] Update tests and examples for Prithvi/Terratorch models (#34416)

2026-02-13 23:03:51 -08:00

plugins_tests

(bugfix): Fixed encode in LLM entrypoint for IOProcessr plugin prompts (#34618)

2026-02-16 07:33:55 -08:00

prompts

…

quantization

[Bugfix] Add regression test for MoE quant_config under torch.compile (#34335)

2026-02-20 13:27:26 +08:00

reasoning

[Feature] Lazy import for the "mistral" tokenizer module. (#34651)

2026-02-23 00:43:01 -08:00

renderers

[Bugfix] Fix edge case in UUID data parsing (#34884)

2026-02-19 02:24:30 -08:00

rocm/aiter

…

samplers

[CI/Build] Try to make beam search test less flaky (#34885)

2026-02-19 19:16:58 +08:00

standalone_tests

[CI][BugFix] ShellCheck cleanup to remove baseline and preserve runtime behavior (#34514)

2026-02-17 12:22:56 +00:00

system_messages

…

tokenizers_

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

tool_parsers

Fix GLM4 parser tests (#34905)

2026-02-24 22:27:42 +08:00

tool_use

…

tools

…

tracing

[CI][Tracing] Fix race condition by adding server readiness check (#34364)

2026-02-16 12:57:39 +00:00

transformers_utils

…

utils_

…

v1

[Linear Attention] fix bug for linear attention + prefix caching + reset_prefix_cache (#35157)

2026-02-24 22:00:19 -08:00

vllm_test_utils

…

weight_loading

…

__init__.py

…

ci_envs.py

…

conftest.py

[CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294)

2026-02-13 20:04:29 -08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_config.py

[Bugfix][CPU] Fix basic unit tests failing in CPU platforms (#34677)

2026-02-25 08:36:15 +00:00

test_embedded_commit.py

…

test_envs.py

…

test_inputs.py

[Refactor] Pass full VllmConfig to Renderer (#34485)

2026-02-12 22:48:38 -08:00

test_logger.py

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

…

test_ray_env.py

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)

2026-02-17 01:08:42 -08:00

test_regression.py

…

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

utils.py

[Refactor] [1/N] Reorganize kernel abstraction directory (#34055)

2026-02-24 06:47:22 +00:00