vincentzed ddb3970eb4 Tiny env cleanup in deepgemm (#15706) ...

Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>

2025-12-24 00:58:46 -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

EP Support for Piecewise Cuda Graph (#14164)

2025-12-20 01:59:27 +08:00

configs

[Feature] support fastsafetensors (#15091)

2025-12-23 22:33:56 +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

Super tiny add more info in dumper (#14145)

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

disaggregation

Support PP for zmq_to_scheduler (#15312)

2025-12-23 17:07:55 +08:00

distributed

[VLM] Support ViT Piecewise CUDA Graph for Qwen3-VL (#15320)

2025-12-20 21:00:07 +08:00

dllm

Tiny extract ModelRunnerOutput (#15400)

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

elastic_ep

…

entrypoints

[model-gateway]: add gRPC router embeddings endpoint implementation (#15273)

2025-12-23 09:12:22 -08:00

eplb

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

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

function_call

Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#15538)

2025-12-23 15:11:52 -08:00

grpc

[model-gateway]: add gRPC router embeddings endpoint implementation (#15273)

2025-12-23 09:12:22 -08:00

hardware_backend/npu

[NPU] [BUGFIX] [CRITICAL!] Fix NPU inference (torch_npu._npu_reshape_and_cache() crash) (#15484)

2025-12-20 14:53:46 +08:00

layers

Tiny env cleanup in deepgemm (#15706)

2025-12-24 00:58:46 -08:00

lora

Feature/Fix multi lora scheduler blocking issue and evict LoRA None lastly (#14795)

2025-12-12 17:13:05 -08:00

managers

[Feature][MM] split the images of one request into multiparts (#11828)

2025-12-24 11:22:04 +08:00

mem_cache

[feature] support hicache-3fs usrbio lib build for ubuntu24.04 (#15230)

2025-12-21 17:00:38 -08:00

metrics

Add kv_transfer_total_mb to metrics (#15667)

2025-12-23 11:16:55 -08:00

model_executor

[Tiny]Move deepseek fp4 cutlass moe test to per-commit test (#15565)

2025-12-21 18:08:07 -08:00

model_loader

[Feature] support fastsafetensors (#15091)

2025-12-23 22:33:56 +08:00

models

Tiny env cleanup in deepgemm (#15706)

2025-12-24 00:58:46 -08:00

multimodal

[GLM-ASR] GLM-ASR Support (#15570)

2025-12-22 17:37:55 -08:00

multiplex

…

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

[2/N] clean duplicate code of logprob processing in spec. (#15593)

2025-12-24 15:21:13 +08:00

tokenizer

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

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

tracing

…

utils

Add kv_transfer_total_mb to metrics (#15667)

2025-12-23 11:16:55 -08:00

weight_sync

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

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

constants.py

…

custom_op.py

…

environ.py

Tiny env cleanup in deepgemm (#15706)

2025-12-24 00:58:46 -08:00

server_args_config_parser.py

…

server_args.py

Simplify server args (#15704)

2025-12-23 22:46:12 -08:00