sglang

arg_groups

Revert "[Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend" (#35568 )

2026-08-19 14:14:38 -07:00

batch_invariant_ops

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

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

batch_overlap

[AMD] Support prefill context parallel two batch overlap for DeepSeek V4 (#33480 )

2026-08-16 22:40:29 -07:00

checkpoint_engine

…

compilation

[Memory] Borrow CUDA graph pool storage for EAGLE sampling (#35375 )

2026-08-18 16:19:41 -07:00

configs

[Qwen3.5][MTP] Preserve online NVFP4 draft quantization for mixed checkpoints (#35545 )

2026-08-19 11:12:32 -07:00

connector

…

constrained

fix(constrained): reject NUL bytes in grammar specs to stop an xgrammar segfault (#34679 )

2026-08-19 15:31:14 -07:00

debug_utils

spec: size the speculative buffers from the bags, not the startup record (#35024 )

2026-08-17 16:16:56 -07:00

disaggregation

[PD] Deferred decode-side KV release for the NIXL backend (#35360 )

2026-08-19 17:29:45 +08:00

distributed

Fix DP attention on CPU (#12961 )

2026-08-19 09:56:21 +08:00

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

feat(openai): Accept the input_audio content part in chat completions (#33606 )

2026-08-19 13:37:50 -07:00

eplb

Add explicit EPLB balancedness reporting modes (#34998 )

2026-08-16 15:31:11 -07:00

function_call

Stop losing Kimi-K3 tool calls to reasoning, constraint conflicts, and truncation (#34881 )

2026-08-18 12:42:56 -07:00

hardware_backend

[NPU] Add mxfp4-w4a4 MOE Quantization Support for NPU (#30319 )

2026-08-18 19:06:05 +03:00

kv_canary

config: the per-instance families read the bags (#35026 )

2026-08-17 16:17:53 -07:00

layers

[Quant] Load compressed-tensors quantized lm_head instead of value-casting it (#35228 )

2026-08-19 15:37:45 -07:00

lora

config: the DP/EP topology reads come from the parallel bag (#35025 )

2026-08-17 16:17:26 -07:00

managers

[Scheduler] Add configurable decode interval after prefill (#35017 )

2026-08-19 12:01:36 -07:00

mem_cache

[HiCache] Simple style change for buffer mode (#35574 )

2026-08-19 15:23:21 -07:00

model_executor

Fix DP attention on CPU (#12961 )

2026-08-19 09:56:21 +08:00

model_loader

quant: extract shared checkpoint quant metadata resolver (#35172 )

2026-08-19 08:26:41 +08:00

models

[Spec] Support quantized target lm_head in the DFlash2 selector (#35496 )

2026-08-19 18:06:41 -07:00

multimodal

fix: fix transcription & audio-understanding for ASR/audio/speech models (#32611 )

2026-08-19 18:44:23 +08:00

multiplex

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

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

observability

[HiCache] Buffer-only mode for HiCache host memory layer (#34798 )

2026-08-18 19:21:24 -07:00

parser

Stop losing Kimi-K3 tool calls to reasoning, constraint conflicts, and truncation (#34881 )

2026-08-18 12:42:56 -07:00

platforms

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

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

plugins

…

ray

config: the per-instance families read the bags (#35026 )

2026-08-17 16:17:53 -07:00

rust_extensions

Build Rust extensions on demand in source checkouts (#34994 )

2026-08-16 14:58:06 -07:00

sampling

[Bugfix] Fix min-new-token EOS handling (#31378 )

2026-08-19 15:29:22 -07:00

session

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

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

speculative

[Spec] Support quantized target lm_head in the DFlash2 selector (#35496 )

2026-08-19 18:06:41 -07:00

state_capturer

Revert "[Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend" (#35568 )

2026-08-19 14:14:38 -07:00

tokenizer

Add Inkling model support (#31681 )

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

utils

[Constrained] Support MistralCommon tokenizers in the XGrammar backend (#35215 )

2026-08-19 12:34:48 +08:00

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

[AMD][MXFP4] Online MXFP4 quantization 1/N - dense and MOE models w. original BF16 weight (#18005 )

2026-06-03 12:55:24 -07:00

cuda_vmm_utils.py

[Memory] Borrow CUDA graph pool storage for EAGLE sampling (#35375 )

2026-08-18 16:19:41 -07:00

environ.py

Revert "[Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend" (#35568 )

2026-08-19 14:14:38 -07:00

runtime_context.py

config: one control-plane log for the process (#35028 )

2026-08-17 16:19:00 -07:00

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

Revert "[Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend" (#35568 )

2026-08-19 14:14:38 -07:00