roikoren755 7c985331dd Enable TP for Mamba-based models (#14811) ...

Signed-off-by: Roi Koren <roik@nvidia.com>

2025-12-10 18:03:50 -08:00

..

batch_invariant_ops

…

batch_overlap

[Misc]Register and refactor some environs for dpsk-fp4 and DeepEp (#14538)

2025-12-06 12:29:16 -08:00

checkpoint_engine

…

compilation

[Auto Sync] Update backend.py (20251130) (#14153)

2025-11-30 22:15:02 -08:00

configs

Revert transformers to 4.57.1 (#14801)

2025-12-10 11:04:36 -08:00

connector

…

constrained

[Reasoning + Structured Output] make reasoning compatible with structured output (#12551)

2025-12-08 01:28:39 -08:00

debug_utils

Super tiny add more info in dumper (#14145)

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

disaggregation

Enhance prefill PP node robustness (#14494)

2025-12-06 18:00:54 -08:00

distributed

Move custom_ops under layers; move _custom_ops.py → custom_all_reduce_ops.py (#14326)

2025-12-03 10:33:37 -08:00

dllm

[DLLM] feat: Add threshold based parallel decoding support (#14412)

2025-12-07 18:25:33 +08:00

elastic_ep

…

entrypoints

Support HTTP response status code prometheus metrics (#14710)

2025-12-10 22:28:57 +08:00

eplb

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

function_call

[Tool Call] Fix DeepSeekV32Detector skipping functions with no params in streaming mode (#14573)

2025-12-07 18:32:10 -08:00

grpc

[misc] add model arch and type to server info and use it for harmony (#14456)

2025-12-05 06:51:00 -08:00

hardware_backend/npu

[NPU] bug fix for mtp and w4a8 (#14806)

2025-12-10 22:55:13 +08:00

layers

Enable TP for Mamba-based models (#14811)

2025-12-10 18:03:50 -08:00

lora

[Feature] Add LoRA support for embedding layers (#14177)

2025-12-09 15:53:33 -08:00

managers

Minor code style fix for dllm (#14836)

2025-12-11 10:35:42 +09:00

mem_cache

[RadixTree] Optimize the Time Complexity of Node Retrieval Operation from O(n*m) to O(n) (#13334)

2025-12-08 15:55:09 -08:00

metrics

[Auto Sync] Add max_total_num_tokens metric: Update scheduler_metrics_mixin.py, collector.py (20251202) (#14256)

2025-12-01 16:34:34 -08:00

model_executor

Minor code style fix for dllm (#14836)

2025-12-11 10:35:42 +09:00

model_loader

fix: restrict cache validation behaviors to CI only (#14849)

2025-12-10 16:03:53 -08:00

models

[bugfix] qwen25-VL support lora (#14638)

2025-12-10 11:38:51 -08:00

multimodal

[Model] Add PaddleOCR-VL Model Support (#12953)

2025-12-09 10:16:02 -08:00

multiplex

…

parser

[Model] Add PaddleOCR-VL Model Support (#12953)

2025-12-09 10:16:02 -08:00

sampling

[Glm46v] Bug fix for accuracy drop and unable to launch server (#14585)

2025-12-07 23:45:02 -08:00

speculative

support mtp with deepseek r1 nvfp4 model (#13115)

2025-12-06 00:45:54 -08:00

tokenizer

…

tracing

…

utils

Treat unittest SkipTest exception as pass instead of as failure (#14847)

2025-12-10 15:28:21 -08:00

weight_sync

…

constants.py

…

custom_op.py

…

environ.py

Add FP8 Blockwise GEMM Backend Flag --fp8-gemm-backend (#14379)

2025-12-09 12:05:56 -08:00

server_args_config_parser.py

…

server_args.py

fix lora target all + csgmv backend (#14796)

2025-12-10 11:42:51 -08:00