Ning Xie c907d22158 [refactor] refactor memory constants usage (#31865) ...

Signed-off-by: Andy Xie <andy.xning@gmail.com>

2026-01-07 18:37:31 +00:00

..

basic_correctness

[refactor] refactor memory constants usage (#31865)

2026-01-07 18:37:31 +00:00

benchmarks

[UX] Make vllm bench serve discover model by default and use --input-len (#30816)

2025-12-17 01:55:30 -08:00

compile

[CI] Add warmup run in test_fusion_attn (#31183)

2026-01-07 00:31:52 +00:00

config

[Core] Parse vLLM engine required fields from hf_config to model_arch_config (#28454)

2026-01-02 15:13:15 -08:00

cuda

…

detokenizer

…

distributed

[Attention] Update tests to remove deprecated env vars (#30563)

2025-12-17 09:49:59 -08:00

engine

Add --max-model-len auto to auto-fit context to available memory (#29431)

2025-12-23 21:37:14 -08:00

entrypoints

[Model] rename use_pad_token to use_sep_token (#31784)

2026-01-06 14:16:04 +00:00

evals

[MoE Refactor] Add Temporary Integration Tests - H100/B200 (#31759)

2026-01-06 10:34:17 -05:00

kernels

[Perf][Kernels] Enable FlashInfer DeepGEMM swapAB on SM90 (for W8A8 Linear Op) (#29213)

2026-01-07 10:53:54 -05:00

lora

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

model_executor

[Chore] Try remove init_cached_hf_modules (#31786)

2026-01-07 12:34:04 +08:00

models

[ROCm][CI] Fix ModernBERT token classification test numerical accuracy on ROCm (#31820)

2026-01-06 23:21:15 +00:00

multimodal

[Frontend] Implement robust video frame recovery for corrupted videos (#29197)

2026-01-07 01:13:24 +00:00

plugins

…

plugins_tests

…

prompts

…

quantization

[Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801)

2026-01-06 19:10:18 +00:00

reasoning

[Chore] Adjust tokenizer import to avoid circular imports (#30601)

2025-12-13 04:42:39 -08:00

rocm/aiter

[Bugfix][Hardware][AMD] Fix exception types in AITER MLA FP8 check (#31177)

2026-01-06 14:10:59 +08:00

samplers

…

standalone_tests

[ROCm][CI] Fix entrypoints tests and Python-only installation test on ROCm (#28979)

2025-12-23 22:42:30 -08:00

system_messages

…

tokenizers_

[CI Failure] Disable mosaicml/mpt-7b and databricks/dbrx-instruct tests (#31182)

2025-12-22 15:40:35 -08:00

tool_parsers

fix: update kimi k2 tool parser logic (#31207)

2025-12-30 10:01:58 +08:00

tool_use

[Bugfix][Frontend] Prevent IndexError in MiniMax M2 tool parser during streaming extraction (#30555)

2025-12-17 16:37:57 +08:00

tools

…

transformers_utils

…

utils_

use the same stream for cuda graph catpure and replay for NCCL (#29207)

2025-12-25 19:10:03 +08:00

v1

[KVConnector]: Enable Cross-layers KV cache layout for MultiConnector (#30761)

2026-01-07 16:59:43 +00:00

vllm_test_utils

…

weight_loading

…

__init__.py

…

ci_envs.py

…

conftest.py

[Model] Nemotron Parse 1.1 Support (#30864)

2026-01-05 13:00:14 -08:00

test_attention_backend_registry.py

[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869)

2025-12-20 09:03:35 +08:00

test_config.py

[Core] Parse vLLM engine required fields from hf_config to model_arch_config (#28454)

2026-01-02 15:13:15 -08:00

test_embedded_commit.py

…

test_envs.py

…

test_inputs.py

Improve parse_raw_prompt test cases for invalid input .v2 (#30512)

2025-12-14 11:18:41 +08:00

test_logger.py

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

…

test_regression.py

…

test_routing_simulator.py

[MoE Refactor][5/N] Isolate zero expert to LongCatFlash (#28891)

2025-12-20 18:22:04 +00:00

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

utils.py

[CI] Add Qwen3-Next-FP8 to Blackwell model tests (#31049)

2025-12-23 17:21:50 -08:00