sglang

arg_groups

introduce arg_groups/ with nemotron_h hook (#24328 )

2026-05-03 16:28:11 -07:00

batch_invariant_ops

Add deterministic mode for XPU operations (#16793 )

2026-04-30 13:39:06 +08:00

batch_overlap

[bugfix] Support MIXED forward mode in TBO splitter for DP attention (#24241 )

2026-05-01 16:01:23 -07:00

checkpoint_engine

update pre-commit config (#18860 )

2026-02-16 00:18:31 +08:00

compilation

Multi platform Plugin (#21388 )

2026-04-19 17:23:51 -07:00

configs

Register deepseek_v32 alias instead of rewriting config.json (#24295 )

2026-05-03 16:02:17 -07:00

connector

Remove sync points in mamba cache + prefill cudagraph plumbing for DP (#19639 )

2026-03-02 15:03:42 +08:00

constrained

[Fix] eagle/eagle3 speculative decoding conflicts with xgrammar in NPU (#20989 )

2026-04-15 23:34:23 -07:00

debug_utils

Add e2e demo test in dump comparator (#21031 )

2026-03-20 22:41:01 +08:00

disaggregation

[PD]: Support incremental transfer for mooncake transfer engine (#24257 )

2026-05-04 00:57:59 +08:00

distributed

Rename SGLANG_USE_JIT_ALL_REDUCE to SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2 (#24297 )

2026-05-02 23:59:46 -07:00

dllm

Decouple scheduler log printing from metrics collection (#20107 )

2026-03-07 22:09:10 -08:00

elastic_ep

[6/N] (Elastic EP) Recover failed ranks (#15771 )

2026-04-28 00:44:26 -07:00

entrypoints

[Dependency] Upgrade to Torch 2.11.0 (#21247 )

2026-05-02 12:25:36 -07:00

eplb

Replace hardcoded CUDA device with get_device() for XPU support (#13599 )

2026-05-01 07:13:46 +08:00

function_call

support Hy3 preview (#23533 )

2026-04-24 12:03:24 -07:00

grpc

[gRPC] Extract gRPC servicer into standalone package (#20478 )

2026-03-13 09:13:29 -07:00

hardware_backend

[MUSA][19/N] Support qwen series models (#23654 )

2026-04-30 11:26:47 -07:00

layers

[NPU]TP Communications compression For Qwen3 models for NPU (#20520 )

2026-05-02 14:29:11 +03:00

lora

feat(lora): enable csgmv backend with virtual experts for MoE LoRA (#24007 )

2026-05-03 18:44:17 -07:00

managers

[UnifiedRadixTree]: Support HiCache Framework for UnifiedRadixTree (#23316 )

2026-05-03 22:13:22 +08:00

mem_cache

[UnifiedRadixTree]: Support HiCache Framework for UnifiedRadixTree (#23316 )

2026-05-03 22:13:22 +08:00

model_executor

extract adjust_hybrid_swa_layers_for_pp (#24334 )

2026-05-03 18:52:54 -07:00

model_loader

fix: accept 0-indexed safetensors shard names in CI weight validator (#24237 )

2026-05-02 00:58:15 -07:00

models

[Dependency] Upgrade to Torch 2.11.0 (#21247 )

2026-05-02 12:25:36 -07:00

multimodal

[Feature] Xiaomi MiMo-V2.5 day0 support (#23811 )

2026-05-01 00:02:26 +08:00

multiplex

[mem] Flatten memory checkers into composable per-pool invariant checks (#22562 )

2026-04-11 02:56:22 -07:00

observability

Refactor device timer, clean up metrics collector, and add fwd occupancy metric (#24197 )

2026-05-01 10:25:25 -07:00

parser

[Feature] Xiaomi MiMo-V2.5 day0 support (#23811 )

2026-05-01 00:02:26 +08:00

platforms

Clean up noisy startup warnings from third-party deps (#23669 )

2026-04-27 03:10:46 -07:00

plugins

Multi platform Plugin (#21388 )

2026-04-19 17:23:51 -07:00

ray

[Ray] Bind scheduler actors to GPU-local NUMA node (#22989 )

2026-04-16 14:52:15 -07:00

sampling

Fix /generate endpoint crash when sampling params contain null values (#23401 )

2026-04-22 09:56:10 -07:00

session

[session] fix mamba pool leak in StreamingSession.release_session + plumb idle leak check (#23496 )

2026-05-02 11:38:08 +08:00

speculative

[Bug Fix] Resolve EAGLE cuda graph IMA under PD + DP + MTP with GLM-5.1 (#23037 )

2026-05-01 13:53:52 -07:00

tokenizer

[Piecewise Cuda Graph] rename, refactor and add more logging (#13675 )

2025-11-21 13:28:38 +08:00

utils

Register deepseek_v32 alias instead of rewriting config.json (#24295 )

2026-05-03 16:02:17 -07:00

weight_sync

…

constants.py

Clean up detokenizer and remove dead multimodal_gen code (#21588 )

2026-03-28 21:44:40 -07:00

environ.py

Rename SGLANG_USE_JIT_ALL_REDUCE to SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2 (#24297 )

2026-05-02 23:59:46 -07:00

server_args_config_parser.py

[ConfigArgumentMerger] Improve ConfigArgumentMerger compatibility with external callers (#17051 )

2026-01-16 15:32:42 +08:00

server_args.py

feat(lora): enable csgmv backend with virtual experts for MoE LoRA (#24007 )

2026-05-03 18:44:17 -07:00