sglang

arg_groups

[Spec] Support MegaMoE for DSpark under dp attention (#34844 )

2026-08-14 17:20:01 -07:00

batch_invariant_ops

[NPU]adaptation to support deterministic inference (#21197 )

2026-06-09 09:22:09 +08:00

batch_overlap

[perf] Collapse the DP attention scheduler sync to a single D2H copy (#34338 )

2026-08-10 21:52:29 -07:00

checkpoint_engine

…

compilation

[Kernel] Unify BaseFusedOp and MultiPlatformOp dispatch (#33205 )

2026-08-06 08:52:09 +08:00

configs

[AMD][Quantization] Online MXFP4 quantization 4/N - NVFP4 to MXFP4 Online Requantization on AMD GPUs (#29328 )

2026-08-14 21:59:39 -07:00

connector

…

constrained

[misc] Pass FP8 scales in FlashInfer SWA prefill, autotune fp8 on SM120, and tighten is_image_understandable_model (#34217 )

2026-08-09 23:45:11 -07:00

debug_utils

config: read resolved config via namespace accessors (#33013 )

2026-07-31 15:06:59 -07:00

disaggregation

[PD] Add the missing Prefill bootstrap timeout for NIXL (#34692 )

2026-08-14 01:08:09 +08:00

distributed

[NVIDIA] Add flashinfer MNNVL backend for allreduce only (#30700 )

2026-08-11 16:46:46 -07:00

dllm

config: read resolved config via namespace accessors (#33013 )

2026-07-31 15:06:59 -07:00

elastic_ep

[Mooncake] Fix ProcessGroup API imports (#32403 )

2026-08-03 01:16:41 -07:00

entrypoints

[Fix] Require JSON booleans for response_format json_schema.strict (#34777 )

2026-08-14 16:46:27 -07:00

eplb

config: route parallel config-leaf reads through get_parallel() (#33170 )

2026-08-01 08:58:39 -07:00

function_call

[Fix] Work around xgrammar 0.2.1 negative integer minimum in Kimi-K3 structural tags (#34778 )

2026-08-14 16:41:06 -07:00

grpc

…

hardware_backend

[Model Loading] Overlap checkpoint staging with CUDA graph capture during startup (#32017 )

2026-08-13 12:26:25 -07:00

kv_canary

Radix Cache Split: Spin off TreeCore (#29901 )

2026-07-25 14:31:59 -07:00

layers

[AMD][Quantization] Online MXFP4 quantization 4/N - NVFP4 to MXFP4 Online Requantization on AMD GPUs (#29328 )

2026-08-14 21:59:39 -07:00

lora

Support Intern-S2-Mobius (#33691 )

2026-08-08 11:06:57 +08:00

managers

[AMD][CI] Fix stage-b: AttributeError on multimodal embedding requests (#34769 )

2026-08-14 21:35:26 -07:00

mem_cache

[Fix] Fix Qwen3.5 MTP startup with HiCache (#34560 )

2026-08-14 10:55:41 -07:00

model_executor

Fix startup weight load after TorchAO removal (#34869 )

2026-08-14 13:18:53 -07:00

model_loader

[AMD][Quantization] Online MXFP4 quantization 4/N - NVFP4 to MXFP4 Online Requantization on AMD GPUs (#29328 )

2026-08-14 21:59:39 -07:00

models

[Spec] Wire DFLASH aux-hidden capture into the Qwen3.5 text-only wrapper (#34771 )

2026-08-14 17:10:09 -07:00

multimodal

[Fix] Carry the backend on Kimi-K3 deferred preprocessing configs (#34766 )

2026-08-13 13:30:33 -07:00

multiplex

config: read resolved config via namespace accessors (#33013 )

2026-07-31 15:06:59 -07:00

observability

metrics: don't clock-rebase unset time sentinels in ReqTimeStats deserialization (#34335 )

2026-08-12 14:27:47 +08:00

parser

[VLM] add content-addressed preprocessing cache infrastructure (#34398 )

2026-08-13 14:09:07 +08:00

platforms

[Kernel] Unify BaseFusedOp and MultiPlatformOp dispatch (#33205 )

2026-08-06 08:52:09 +08:00

plugins

…

ray

config: pass the Ray placement group as a launch argument

2026-08-05 19:28:39 -07:00

sampling

Support thinking budget for Inkling (#33146 )

2026-08-11 02:01:08 +08:00

session

feat: add cache salt support to KV cache events (#30827 )

2026-08-12 16:14:04 -07:00

speculative

[Perf] Publish the WAR read-done event at DSPARK verify (#34816 )

2026-08-14 00:46:52 -07:00

state_capturer

[Fix: RL] Snapshot async state-capture outputs before overlap (#34319 )

2026-08-14 16:39:35 -07:00

tokenizer

Add Inkling model support (#31681 )

2026-07-19 22:57:37 -07:00

utils

[Fix] has_hf_quant_config crashes on local dirs without the config (#34774 )

2026-08-14 07:17:42 +00:00

weight_cache

config: route parallel config-leaf reads through get_parallel() (#33170 )

2026-08-01 08:58:39 -07:00

weight_sync

Introduce WeightUpdater and WeightExporter components (#31148 )

2026-07-14 15:53:33 +08:00

constants.py

…

cuda_vmm_utils.py

Fix CUDA 13.0 VMM handle type compatibility (#34431 )

2026-08-11 15:16:34 -07:00

environ.py

fix(scheduler): track max prefill batch size over recent real admissions (#34284 )

2026-08-15 10:48:03 +08:00

runtime_context.py

Fix mamba checkpoint depth under dcp (#34808 )

2026-08-15 00:34:00 +08:00

server_args_config_parser.py

fix(server): serialize nested dict config values as JSON (#28094 )

2026-06-12 19:27:31 -07:00

server_args.py

[AMD][Quantization] Online MXFP4 quantization 4/N - NVFP4 to MXFP4 Online Requantization on AMD GPUs (#29328 )

2026-08-14 21:59:39 -07:00