Michael GoinandOpenAI Codex 275556c35c [Bugfix] Detect mixed precision in packed KV cache specs (#49623) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-07-23 20:07:06 -07:00

..

basic_correctness

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

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

benchmarks

[Bugfix] Re-enable benchmarking of librispeech dataset. (#47033)

2026-07-08 16:19:26 +00:00

compile

[Model][Hardware][AMD]: Part 1/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_AITER_FA, and ROCM_AITER_UNIFIED_ATTN (#42749)

2026-07-16 17:39:04 -05:00

config

[Bugfix] Exclude location-derived path vars from torch.compile cache factors (#47573)

2026-07-22 16:56:09 -07:00

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

[Bugfix][Core] shm_broadcast: bound idle reader waits and release read slots (#45224)

2026-07-23 18:13:29 +08:00

engine

[Misc][Docs] Add human-readable integer support for more cli-args (#47608)

2026-07-08 09:43:34 +00:00

entrypoints

[CI] Disable reasoning in Responses smoke test (#49511)

2026-07-23 19:02:54 +00:00

evals

[Bugfix][Attention] Ignore empty MLA context chunks during merge (#49294)

2026-07-22 02:23:48 +00:00

fusion

…

ir

…

kernels

[CI][Bugfix] Fix test isolation in block_int8/ptpc_fp8 MoE kernel tests (#49609)

2026-07-23 12:26:02 -05:00

lora

[BugFix][LoRA] Skip marlin-backend gpt-oss LoRA tests on XPU (#49385)

2026-07-24 09:16:00 +08:00

model_executor

[Bugfix][SpecDecode] Scope MTP completeness checks outside bucketed updates (#49178)

2026-07-21 18:56:39 -07:00

models

[Model] Support llm-compressor Inkling NVFP4 weights (#49258)

2026-07-23 20:06:01 -07:00

multimodal

[Misc] Move PyNvVideoCodec stuff out of gpu worker (#49322)

2026-07-22 10:11:56 +08:00

parser

[Bugfix][Parser] Fix special tokens (EOS/BOS) leaking into reasoning content (#48748)

2026-07-22 16:10:55 -04:00

plugins

[bugfix] bge-m3-sparse-plugin mismatch requests (#48112)

2026-07-10 10:03:00 +08:00

plugins_tests

[CI][Bugfix] Reduce max_model_len in OOT embedding test to fix KV-cache OOM on small GPUs (#49351)

2026-07-21 15:00:06 -04:00

prompts

…

quantization

[ROCm][Quantization] Add Quark W4A8 (INT4-FP8) MoE CI coverage (#48050)

2026-07-23 21:56:40 -05:00

reasoning

…

renderers

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

rocm/aiter

…

samplers

…

spec_decode

…

standalone_tests

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

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

system_messages

…

tokenizers_

[Bugfix] Fix logprobs token-string collision from SentencePiece space… (#48674)

2026-07-20 12:17:18 +08:00

tool_parsers

[Bugfix][Tool Parser] Preserve whitespace in parameter values (MiniMax M2, Qwen3, MiniCPM5 XML) (#48846)

2026-07-17 16:45:41 +00:00

tool_use

[Bugfix] Fix parallel_tool_calls=null crash in Responses API from_request() (#48098)

2026-07-15 18:01:17 +08:00

tools

…

tracing

…

transformers_utils

…

utils_

[copy of #45208] CuMem slept-L1 fragmentation accounting (#49208)

2026-07-20 23:08:11 +00:00

v1

[Bugfix] Detect mixed precision in packed KV cache specs (#49623)

2026-07-23 20:07:06 -07:00

vllm_test_utils

…

weight_loading

…

__init__.py

…

ci_envs.py

…

conftest.py

[Bugfix][CI/Build] Fix Plamo2 HF runner crash on transformers v5 (_tied_weights_keys list→dict) (#44239)

2026-07-23 12:25:14 +00:00

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_config.py

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

test_embedded_commit.py

…

test_envs.py

[KVOffload][P2P] Well-known default host/port env vars and per-DP-rank control port (#47636)

2026-07-15 15:22:56 +03:00

test_force_first_config.py

…

test_fxgraphcache_pickle_patch.py

…

test_inputs.py

…

test_jit_monitor.py

Bump flashinfer version to 0.6.14 (#47669)

2026-07-15 21:00:40 -07:00

test_logger.py

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

[Bugfix] Reject removed pooling parameters (#48984)

2026-07-19 05:18:03 -07:00

test_ray_env_utils.py

…

test_ray_env.py

…

test_regression.py

…

test_sampling_params.py

[Bugfix] Reject sampling params unsupported by diffusion models (#45418)

2026-07-07 11:25:36 +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

…

utils.py

[CI] Move compatible 1xL4 jobs to H200 35GB MIG (#43024)

2026-07-19 19:21:25 -07:00