Chen Haozhe 6c2e5fcd91 [feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

..

batch_invariant_ops

Support fast gemm when in batch invariant DeepGEMM fallback (#13259)

2025-11-15 16:34:15 +08:00

checkpoint_engine

…

compilation

[2 / 2] apply sgl-kernel weak_ref_tensor (#12978)

2025-11-16 21:24:35 +08:00

configs

[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

connector

…

constrained

[Ascend]support xgrammar backend for ascend npu (#12310)

2025-11-15 19:39:24 -08:00

debug_utils

Add script to create a model with fewer layers for debugging (#13284)

2025-11-14 22:13:27 +08:00

disaggregation

[PD] Clarify init method docstrings for kvsender and kvreceiver (#13476)

2025-11-18 12:20:19 +08:00

distributed

fix uneven PP layer indices (#13282)

2025-11-17 19:54:23 +08:00

elastic_ep

…

entrypoints

[GLM4.6v] Relax the constraint of non-user role chat completion message schema for new GLM-v release (#13258)

2025-11-18 10:58:17 +08:00

eplb

Fix dpsk-r1-fp4 tp8 by reverting two commits (#13162 and #13341) (#13348)

2025-11-15 21:31:36 -08:00

function_call

[Tool Call] Steamline function arguments when tool_choice="auto" for deepseekv31_detector (#11589)

2025-11-13 23:06:02 -08:00

grpc

Add timing metrics for requests (#12646)

2025-11-05 23:07:16 -08:00

layers

[fix] Fixes accuracy issues caused by incorrect use of rope (#13495)

2025-11-18 14:17:33 -08:00

lora

Small cleanups related to LoRA weight loading (#13474)

2025-11-18 09:14:34 -08:00

managers

[HiCache] Critical fix to host memory double free (#13501)

2025-11-18 01:34:23 -08:00

mem_cache

[Feature] Re:Enable hybrid mem saver (#12962)

2025-11-18 21:29:15 +08:00

metrics

refine stdout logging codes (#13015)

2025-11-12 00:16:14 +08:00

model_executor

[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

model_loader

[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

models

[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

multimodal

[VLM][feat] Support encoder DP for Qwen2.5-VL (#13126)

2025-11-18 16:13:18 +08:00

multiplex

[Feature] PD-Multiplexing Context and Scheduler, lazy import spatial. (#12275)

2025-11-01 00:40:01 +08:00

parser

add Kimi k2 reasoning parser (#12702)

2025-11-06 00:37:54 +08:00

sampling

[Bug] OOM (Out-of-Memory) errors for extreme testing scenarios (min_tokens=2) (#11757)

2025-11-01 00:28:41 +08:00

speculative

[Feature] Spec-Overlap supporting DP-ATTN; PD-Disaggregation; npugraph mode (#12443)

2025-11-15 21:51:07 +08:00

tokenizer

…

tracing

[minor] remove debug code in python/sglang/srt/compilation/weak_ref_tensor_jit.py (#13235)

2025-11-14 12:22:24 -08:00

utils

model: support JetVLM (#13289)

2025-11-18 12:02:03 +08:00

weight_sync

…

_custom_ops.py

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

constants.py

…

custom_op.py

…

environ.py

Add SGLANG_ENABLE_REQ_POOL_LEAK_STRICT_CHECK to bypass mem leak check (#13339)

2025-11-16 22:02:22 +08:00

operations_strategy.py

…

operations.py

Register allgather/reducescatter buffers with symm memory (#12572)

2025-11-04 17:11:36 -08:00

server_args_config_parser.py

…

server_args.py

[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

2025-11-19 09:17:47 +08:00

single_batch_overlap.py

…

two_batch_overlap.py

Minor code cleanup / improvement for PREBUILT_EXTEND mode (#12948)

2025-11-10 11:59:54 +08:00

warmup.py

…