sglang

hf_transformers

config: the runtime readers take the published bags (#36254 )

2026-08-26 05:08:25 -07:00

__init__.py

…

aio_rwlock.py

…

aiter.py

Clean up prefill CUDA graph runner (#31654 )

2026-07-20 12:14:21 -07:00

async_probe.py

[VLM] Avoid synchronizing multimodal placeholder counts (#34995 )

2026-08-16 15:15:49 -07:00

auth.py

…

bench_utils.py

[CI] Add per-job uv venv isolation and upgrade CI version to Cuda 13 (#23119 )

2026-04-19 05:32:36 -07:00

common.py

config: the runtime readers take the published bags (#36254 )

2026-08-26 05:08:25 -07:00

cuda_ipc_transport_utils.py

fix(vlm): stream-order cuda-ipc feature pool lifecycle and streamline multimodal transport module (#33949 )

2026-08-10 18:47:19 +08:00

cuda_vmm_transport_utils.py

config: stop handing the record to code that does not read it (#36252 )

2026-08-26 05:02:17 -07:00

cuda_vmm_utils.py

chore: move cuda_vmm_utils.py under srt/utils/ (#36053 )

2026-08-23 21:47:29 -07:00

cudacore_pyspy_dump_utils.py

Trigger scheduler diagnostics on health failure (#26757 )

2026-06-03 17:19:55 -07:00

custom_op.py

[Misc] Clean up python/sglang package structure (#35062 )

2026-08-17 14:24:35 -07:00

device_timer.py

[Fix] Count multi-layer draft-extend replays in the fwd-occupancy device timer (#32867 )

2026-07-30 00:21:34 -07:00

field_validators.py

API Perf: Replace pydantic per-element validation with C loop validation (#26355 )

2026-05-27 02:04:07 -07:00

flatten.py

support rust sglang server (#29799 )

2026-07-31 11:56:31 -07:00

gauge_histogram.py

…

hf_transformers_patches.py

fix: fix Kimi-VL encoder parallelism (#30869 )

2026-07-14 08:44:06 +08:00

hf_transformers_utils.py

Upgrade transformers to 5.5.3 and refactor hf_transformers_utils into subpackage (#21569 )

2026-04-15 20:03:44 -07:00

host_shared_memory.py

…

http_middleware_patch.py

…

invariants.py

[Feature] Add leveled invariant-check primitive for nan/inf/oob validity checks (#32308 )

2026-07-24 04:27:20 -07:00

json_response.py

UX: clean loggings (#22174 )

2026-04-08 09:46:38 +08:00

log_utils.py

Improve metrics, observability, and PD deploy tooling (#24521 )

2026-05-06 11:27:35 -07:00

model_file_verifier.py

…

msgpack_utils.py

feat: make mm_inputs msgpack-native (#29656 )

2026-08-20 14:30:07 -07:00

msgspec_utils.py

Empty _REQ_TYPES_WITH_OPAQUE_FIELDS on the msgpack IPC path (#29465 Task 4) (#30182 )

2026-07-15 14:55:06 -07:00

multi_stream_utils.py

[refactor] Add the per-forward flags tier: ctx.forward (#30490 )

2026-07-09 02:09:03 -07:00

network.py

[Fix] Make wait_port_available actually wait timeout_s seconds (#33086 )

2026-08-10 17:35:50 -07:00

numa_utils.py

[CPU] Fix NUMA/core binding for DP ranks (#32856 )

2026-08-24 12:15:38 +08:00

nvjpeg_decoder.py

fix(vlm): preserve Kimi-K3 GPU JPEG accuracy (#34163 )

2026-08-10 09:42:52 +08:00

nvtx_pytorch_hooks.py

…

nvtx_utils.py

Unify NVTX annotation helpers and split the enable gate per subsystem (#28165 )

2026-06-14 00:04:59 -07:00

offloader.py

config: stop handing the record to code that does not read it (#36252 )

2026-08-26 05:02:17 -07:00

patch_tokenizer.py

bugfix for npu Grok2 model --detokenizer without all special ids (#29853 )

2026-07-02 22:12:48 +08:00

patch_torch.py

[MUSA] Use MUSA-optimized operators in piecewise CUDA graph (#23633 )

2026-05-11 17:55:27 -07:00

phase_checker.py

Add a SimplePhaseChecker for execution-phase assertions (#26803 )

2026-05-31 09:51:39 +08:00

poll_based_barrier.py

…

profile_merger.py

…

profile_utils.py

Profiling Enhancements [2/3]: detailed execution step annotations (#24911 )

2026-08-18 01:09:07 -07:00

rank_consensus_checker.py

TP/PP Consensus checker (#34406 )

2026-08-21 01:36:03 +08:00

request_logger.py

[Refactor] New EPD (#30398 )

2026-08-21 15:22:48 +08:00

rpd_utils.py

chore: cleanup garbage code (#29770 )

2026-07-02 16:14:01 +08:00

runai_utils.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

scheduler_status_logger.py

[lint] Enable Ruff UP037 to drop redundant quoted annotations (#27984 )

2026-06-11 17:38:05 -07:00

slow_rank_detector.py

…

stale_shm_cleanup.py

[misc] Remove break-graph debug log; reclaim pid-less /dev/shm leaks in CI (#33929 )

2026-08-06 21:18:01 -07:00

tensor_bridge.py

[MLX] Upgrade to Torch 2.13/MLX 0.32+ and redesign the Torch-MLX tensor bridge (#32984 )

2026-08-21 18:51:42 -07:00

token_sequence_matcher.py

[Kimi K3] Add reasoning, tool-call, and OpenAI serving support (#33025 )

2026-08-01 14:57:23 -07:00

torch_memory_saver_adapter.py

…

torch_npu_patch_utils.py

[NPU]Support torch_npu profiler patch API drift (#26356 )

2026-06-06 16:27:51 +03:00

triton_load_watch.py

Reland serving-time Triton load diagnostics (#33908 )

2026-08-07 14:51:43 -07:00

video_decoder.py

perf(mimo-v2-epd): enable GPU image preprocess and parallel video decode (#25588 )

2026-05-19 11:47:21 +08:00

watchdog.py

Trigger scheduler diagnostics on health failure (#26757 )

2026-06-03 17:19:55 -07:00

weight_checker_comparator.py

[RL] Support FlashInfer TRT-LLM NVFP4 MoE in the RL weight checker (#31085 )

2026-07-24 16:01:54 -07:00

weight_checker.py

[AMD] Preserve the AITER expert mask across torch_memory_saver pause/resume (#34220 )

2026-08-10 19:59:15 -07:00

weight_versions.py

Report per-token weight-version spans in generation meta info (#35926 )

2026-08-24 20:18:52 +08:00