sglang

batch_invariant_ops

Fix batch invariant ops (#11368 )

2025-10-10 20:49:08 -07:00

checkpoint_engine

[Feature] Support loading weights from ckpt engine worker (#11755 )

2025-10-23 09:23:30 -07:00

compilation

Eager Compiler for Torch Compile (#11803 )

2025-10-18 15:18:52 +08:00

configs

适配w8a8模型

2025-10-29 09:06:22 +08:00

connector

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685 )

2025-10-17 16:49:46 -07:00

constrained

[Feature] New structural tag support (#10691 )

2025-10-20 18:25:58 +08:00

debug_utils

Tiny improve dumper (#11132 )

2025-10-02 17:55:01 +08:00

disaggregation

[lint] improve ruff check (#11922 )

2025-10-22 11:32:50 +08:00

distributed

enable custom_allreduce

2025-11-04 09:33:24 +00:00

elastic_ep

[2/N] Added the core structure of elastic EP and the eplb algorithm with faulty rank (#10606 )

2025-10-22 01:13:31 -07:00

entrypoints

[Feature] Support loading weights from ckpt engine worker (#11755 )

2025-10-23 09:23:30 -07:00

eplb

[2/N] Added the core structure of elastic EP and the eplb algorithm with faulty rank (#10606 )

2025-10-22 01:13:31 -07:00

function_call

Tiny fix main lint (#11862 )

2025-10-20 19:57:24 +08:00

grpc

[grpc] Support gRPC standard health check (#11955 )

2025-10-22 16:59:09 -07:00

layers

V0.5.4 dev linhai

2025-11-04 12:04:47 +00:00

lora

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685 )

2025-10-17 16:49:46 -07:00

managers

增加hipprof支持、修复异步调度中的同步问题

2025-10-28 16:25:06 +08:00

mem_cache

Fix mamba radix cache eviction logic in alloc_req_slots (#11616 )

2025-10-23 13:07:43 -07:00

metrics

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685 )

2025-10-17 16:49:46 -07:00

model_executor

V0.5.4 dev linhai

2025-11-04 12:04:47 +00:00

model_loader

model: support deepseek-ocr (#11891 )

2025-10-24 03:15:17 +08:00

models

V0.5.4 dev linhai

2025-11-04 12:04:47 +00:00

multimodal

model: support deepseek-ocr (#11891 )

2025-10-24 03:15:17 +08:00

parser

model: support deepseek-ocr (#11891 )

2025-10-24 03:15:17 +08:00

profile

增加hipprof支持、修复异步调度中的同步问题

2025-10-28 16:25:06 +08:00

sampling

Support Thinking Budget (via custom_logit_processor for OpenAI API) [Fix #6572 ] (#11416 )

2025-10-21 16:27:56 +08:00

speculative

Fix flush cache API for spec v2 (#11918 )

2025-10-21 23:01:16 +08:00

tokenizer

move more files under srt/utils (#11285 )

2025-10-09 16:46:15 -07:00

tracing

Fix metrics and request tracing (TimeStats) (#11123 )

2025-10-01 13:03:07 -07:00

utils

model: support deepseek-ocr (#11891 )

2025-10-24 03:15:17 +08:00

weight_sync

Tiny move files to utils folder (#11166 )

2025-10-03 22:40:06 +08:00

_custom_ops.py

enable custom_allreduce

2025-11-04 09:33:24 +00:00

constants.py

Multi-Stage Awake: Support Resume and Pause KV Cache and Weights separately (#7099 )

2025-06-19 00:56:37 -07:00

custom_op.py

enable llama3.1-8B on xpu (#9434 )

2025-09-07 22:34:20 -07:00

environ.py

[Fix] memory leak by overlap + retract (#11981 )

2025-10-23 22:59:23 +08:00

operations_strategy.py

[5/N] MoE Refactor: Update MoE parallelism arguments (#8658 )

2025-08-01 01:20:03 -07:00

operations.py

Add fp4 quantize before all-gather for Flashinfer cutlass MoE DP (max throughput) (#7667 )

2025-08-15 22:08:11 -07:00

server_args_config_parser.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685 )

2025-10-17 16:49:46 -07:00

server_args.py

V0.5.4 dev linhai

2025-11-04 12:04:47 +00:00

single_batch_overlap.py

[9/N] MoE Refactor: cleanup dispatcher interfaces (#11847 )

2025-10-20 10:11:46 -07:00

two_batch_overlap.py

[9/N] MoE Refactor: cleanup dispatcher interfaces (#11847 )

2025-10-20 10:11:46 -07:00

warmup.py

[Auto Sync] Update scheduler_profiler_mixin.py, rpd_utils.p... (20250916) (#10494 )

2025-09-16 17:02:20 -07:00