Yifan Qiaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> ffee32460d [BugFix][Mooncake] Use global data_parallel_index for the DP engine index (#48061) ...

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-04 17:10:51 -07:00

..

basic_correctness

[CI] Detect and fail evals on when NaNs appear in logits (#50323)

2026-08-04 23:02:58 +00:00

benchmarks

[Benchmark] Add probe requests to vllm bench serve (#49611)

2026-08-01 22:10:56 +08:00

compile

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

config

[Multimodal] Expose mm hash algothrim selection to cli args (#49686)

2026-07-31 05:25:19 +00:00

cuda

Fix NVML capability lookup for visible devices (#47892)

2026-07-08 09:07:44 -04:00

detokenizer

[Bugfix][Spec Decode] Select earliest-completing stop string in check_stop_strings (#49391)

2026-07-23 18:14:06 +08:00

distributed

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

engine

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

entrypoints

feat(frontend): session id plumbing into requests (#48048)

2026-08-03 22:18:58 +00:00

evals

[CI] Stabilize GLM-5.2 PCP evaluation (#51015)

2026-08-04 14:13:59 -07:00

fusion

Add the QuantizedActivation linear-kernel contract (#44260)

2026-06-12 13:48:15 -07:00

ir

[Perf] Set IR Op Priority Once at Worker Init (#42631)

2026-05-15 15:56:13 +00:00

jit_monitor

[Kernel][CI] --jit-monitor-mode error e2e tests for kernel warmup infra (#50109)

2026-07-31 08:53:16 -04:00

kernels

[Kernel] Add support for Flashinfer Mamba SSU algorithm selection (#50157)

2026-08-04 09:40:23 -07:00

lora

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

model_executor

[Bugfix][MoE] Filter packed expert weights during EP loading (#49558)

2026-08-04 16:32:03 +00:00

models

[Kimi K3 Perf] option to shard the shared expert for non mega case, 16.98 GiB memory/GPU saved (#50912)

2026-08-04 14:00:44 -04:00

multimodal

[Bugfix] Emit a valid media type from encode_{audio,image,video}_url (#49056)

2026-08-03 19:02:23 +00:00

parser

[GPT-OSS] Strict tool call and constrained decoding for Harmony (#45560)

2026-08-01 12:10:26 -04:00

plugins

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

plugins_tests

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

prompts

…

quantization

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

reasoning

[Bugfix][Reasoning] kimi_k3: O(delta) reasoning-end check on the decode path (#50886)

2026-08-04 10:37:03 +08:00

renderers

[Frontend] Cohere chat v2 api support (#47189)

2026-07-31 22:53:54 -07:00

rocm/aiter

[ROCm] Fix AITER FP8 quantization schema tests (#46414)

2026-06-24 22:29:19 +08:00

samplers

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

spec_decode

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

standalone_tests

[CI][AMD] Configure MI300 tests for native execution without DinD (#48387)

2026-07-15 02:14:16 +00:00

system_messages

…

tokenizers_

[Frontend] DeepSeek V4 0731 reasoning effort prompts & mappings (#50580)

2026-08-04 08:51:32 -07:00

tool_parsers

[GPT-OSS] Strict tool call and constrained decoding for Harmony (#45560)

2026-08-01 12:10:26 -04:00

tool_use

[Frontend][Bugfix] Use default tool call IDs for Kimi K3 for conversation-level uniqueness (#50420)

2026-07-31 10:02:17 +08:00

tools

[ROCm][CI] Adding metadata (#47477)

2026-07-02 17:45:23 -07:00

tracing

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

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

transformers_utils

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

utils_

[Core] Explicitly manage torch CPU threads in workers (#49919)

2026-08-04 10:06:38 -07:00

v1

[BugFix][Mooncake] Use global data_parallel_index for the DP engine index (#48061)

2026-08-04 17:10:51 -07:00

vllm_test_utils

…

weight_loading

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

__init__.py

…

ci_envs.py

…

conftest.py

[CI] Retry Hugging Face processor loading (#49908)

2026-07-31 08:48:08 +08:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_cmake_utils.py

[Build] Fix CUDA arch detection producing kernel-less builds on SM121 (#49904)

2026-07-27 22:01:56 -07:00

test_config.py

[New model] Kimi K3 (#50000)

2026-07-30 03:49:58 -07:00

test_embedded_commit.py

…

test_envs.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_force_first_config.py

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

2026-06-16 15:16:45 +02:00

test_fxgraphcache_pickle_patch.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205)

2026-04-10 08:29:35 +00:00

test_inputs.py

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

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

test_logger.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_ray_env_utils.py

[Feat][Executor] Introduce RayExecutorV2 (#36836)

2026-04-01 14:34:29 -07:00

test_ray_env.py

fix nixl side-channel host selection (#41806)

2026-05-11 07:40:37 +00:00

test_regression.py

[CI/Build] Use modelscope's international site for regression test (#42176)

2026-05-09 19:47:09 -07:00

test_sampling_params.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_scalartype.py

…

test_sequence.py

…

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)

2026-03-15 23:35:35 +00:00

utils.py

[CI] Organize speculative decoding E2E tests by coverage (#50330)

2026-07-31 18:05:42 -07:00