3 people 00e607111a [Auto Sync] Update request_metrics_exporter.py (20251230) (#16183) ...

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Scott Lee <scottjlee@users.noreply.github.com>

2025-12-30 11:09:41 -08:00

..

batch_invariant_ops

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

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

batch_overlap

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

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

checkpoint_engine

[Ckpt Engine] feat: new sglang entrypoint support for update (#12216)

2025-10-30 10:39:27 +08:00

compilation

Custom All Reduce for Piecewise Cuda Graph (#15356)

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

configs

Separate swa and local attention chunk cache eviction (#15820)

2025-12-26 09:34:22 +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

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

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

debug_utils

Super tiny add more info in dumper (#14145)

2025-11-30 09:07:39 +08:00

disaggregation

Add profiling capture support to the encoder server (#15730)

2025-12-30 19:56:25 +08:00

distributed

[HiCache] Fix deadlock when creating new group (#15805)

2025-12-29 17:13:04 +08:00

dllm

Tiny extract ModelRunnerOutput (#15400)

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

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

[model-gateway] Add classification model support infrastructure (#16061)

2025-12-29 08:34:05 -08:00

eplb

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

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

function_call

[Tool Call][DSV32] Streamline function call parameters (#14750)

2025-12-26 11:35:30 -08:00

grpc

[model-gateway] Add classification model support infrastructure (#16061)

2025-12-29 08:34:05 -08:00

hardware_backend/npu

[NPU] Support w4a8 with activation clip (#14736)

2025-12-27 16:19:46 +08:00

layers

[Refactor] Rename CustomOp -> MultiPlatformOp (#16175)

2025-12-31 01:16:32 +08:00

lora

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

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

managers

[Auto Sync] Update request_metrics_exporter.py (20251230) (#16183)

2025-12-30 11:09:41 -08:00

mem_cache

Add host tensor allocator for memory_pool_host and support Mooncake standalone storage (#14873)

2025-12-28 16:28:50 -08:00

metrics

Add LoRA metrics for potential auto scaling (#15149)

2025-12-24 12:13:52 -08:00

model_executor

[Refactor] Rename CustomOp -> MultiPlatformOp (#16175)

2025-12-31 01:16:32 +08:00

model_loader

Fix metrics (#15998)

2025-12-28 05:03:49 -08:00

models

Fusing RMSNormTP in minimax_m2 (#14416)

2025-12-30 10:22:07 -08:00

multimodal

[VLM] Support Video for InternVL3_5 (#15942)

2025-12-30 17:07:49 +08:00

multiplex

hotfix: add type hints to scheduler mixins (#15916)

2025-12-26 17:08:11 -08:00

parser

fix: prevent points regex from matching checkpoints/endpoints (#15120)

2025-12-17 12:38:18 -08:00

sampling

Add customized sampler registration (#15423)

2025-12-18 23:10:23 -08:00

speculative

Refactor speculative algorithm registry. (#16168)

2025-12-31 01:24:22 +08:00

tokenizer

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

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

tracing

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

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

utils

Reworked fast_pos_embed_interpolate() using torch (#10959)

2025-12-30 14:45:34 +08:00

weight_sync

[RL] Allow passing tensors of different dtypes for FlattenedTensorBucket (#13413)

2025-11-19 17:24:48 +08:00

constants.py

Support releasing CUDA graph memory when paused (#7873)

2025-10-28 14:40:50 +08:00

environ.py

Add host tensor allocator for memory_pool_host and support Mooncake standalone storage (#14873)

2025-12-28 16:28:50 -08:00

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

dp-attention: add follow_bootstrap_room + auto load-balance; drop decode_round_robin (#16110)

2025-12-30 22:33:06 +08:00