Yingchun Lai 913b688f21 fix: fill a meaningful tool_index (#16504)

2026-01-06 20:00:09 -08:00

..

batch_invariant_ops

…

batch_overlap

[Feature] Xiaomi MiMo-V2-Flash day0 support (#15207)

2025-12-19 11:40:07 +08:00

checkpoint_engine

…

compilation

Custom All Reduce for Piecewise Cuda Graph (#15356)

2025-12-25 23:55:15 +08:00

configs

Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00

connector

…

constrained

Adding tool calling and reasoning parser support for Intern-S1 (#14866)

2025-12-16 00:01:58 -08:00

debug_utils

Support multiple engines for router simulation in schedule simulator (#16368)

2026-01-04 11:46:05 +08:00

disaggregation

[HiCacheStorage & PD] fix prefill bootstrap request host memory leaks (#15439)

2026-01-07 11:03:57 +08:00

distributed

ci(test): migrate OpenAI server tests to registered CI system (#16326)

2026-01-06 11:09:37 -08:00

dllm

Tiny extract ModelRunnerOutput (#15400)

2025-12-18 22:18:45 +08:00

elastic_ep

…

entrypoints

[VLM] Support request level max_dynamic_patch for OpenAI request (#16268)

2026-01-04 13:04:43 +08:00

eplb

Support EPLB balancedness prometheus metric without GPU->CPU synchronize (#15401)

2025-12-18 22:24:23 +08:00

function_call

fix: fill a meaningful tool_index (#16504)

2026-01-06 20:00:09 -08:00

grpc

Revert "[grpc] update api to scheduler in grpc request manager" (#16387)

2026-01-04 22:05:39 -08:00

hardware_backend/npu

[DeepSeek v3.2] opt Context Parallelism: support fused moe, multi batch and fp8 kvcache (#13959)

2026-01-02 23:49:14 +08:00

layers

[FP8] Fix weight_scale shape to match with x_scale shape for per-tensor quant under torch.compile (#16356)

2026-01-05 13:55:26 -08:00

lora

[LoRA] Torch native backend: rework implementation and updated tests (#15187)

2025-12-30 11:48:51 +08:00

managers

[VLM] Fix CUDA IPC OOM (#16118)

2026-01-07 11:30:35 +08:00

mem_cache

Fix evict swa for overlap scheduler and page size > 1 (#16507)

2026-01-06 22:29:40 +08:00

metrics

Tiny add metrics for prefill delayer (#16603)

2026-01-07 09:53:52 +08:00

model_executor

Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00

model_loader

[Auto Sync] Update loader.py (20260105) (#16478)

2026-01-05 01:34:30 -08:00

models

Fix the problem where Qwen3VL raises an "object has no attribute 'mod… (#15677)

2026-01-06 08:45:13 +08:00

multimodal

[VLM] Fix CUDA IPC OOM (#16118)

2026-01-07 11:30:35 +08:00

multiplex

Fix deprecation warning of sre_parse for python 3.13 (#16247)

2025-12-31 21:25:09 -08:00

parser

[VLM] Support request level max_dynamic_patch for OpenAI request (#16268)

2026-01-04 13:04:43 +08:00

sampling

Support returning customized info (#16144)

2026-01-02 15:32:18 +08:00

speculative

[SPEC_V2] Fix Acclen drop when enabling DP Attention for Spec-Overlap (#16310)

2026-01-05 11:39:23 +08:00

tokenizer

…

tracing

SGLang Tracing: fix attribute errors (header extraction & bootstrap span closing) (#15693)

2025-12-27 22:44:31 -06:00

utils

Tiny support sglang_routing_keys_active in engine (#16570)

2026-01-06 22:10:10 +08:00

weight_sync

…

constants.py

…

environ.py

Fix TokenizerManager bottleneck for offline generation (#16456)

2026-01-05 16:28:25 +08:00

server_args_config_parser.py

Fix parse args from file(#13911) (#14085)

2026-01-01 11:37:33 +08:00

server_args.py

Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00