iHore/vLLM

Files

T

History

e77daef89e [Model] Support DeepSeek-V4.1-Flash (#56214 )

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: andyluo7 <andy.luo@amd.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-11 02:11:19 -07:00

..

[Model Runner V2] Support num NaNs in logits (#30187 )

2025-12-09 10:00:49 -08:00

[Core][Model] Unify XD-RoPE into M-RoPE and derive the channel count (#56078 )

2026-09-09 09:23:30 -07:00

[Core] MRV2 support for fast-prefill (#56145 )

2026-09-10 10:36:04 -07:00

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464 )

2026-08-24 08:33:32 -04:00

[feature] Watermarked generation and detection (Gumbel-max algorithm) (#54053 )

2026-09-09 21:00:15 -07:00

[Model] Support DeepSeek-V4.1-Flash (#56214 )

2026-09-11 02:11:19 -07:00

__init__.py

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

async_utils.py

[Perf][Model Runner V2] Compact sampling masks on GPU instead of unpacking the full-vocab bitmask on CPU (#54901 )

2026-09-03 19:03:36 -07:00

attn_utils.py

[Core] MRV2 support for fast-prefill (#56145 )

2026-09-10 10:36:04 -07:00

block_table.py

[Model] Support Qwen3.8-Flash-Next (#53896 )

2026-08-31 05:57:56 +00:00

buffer_utils.py

[Perf] Use UVA-backed contents for MRV2 apply_write (#55819 )

2026-09-10 07:27:16 -07:00

cp_utils.py

[Bugfix][MRV2] Initialize DCP metadata after batch partitioning (#55212 )

2026-09-10 06:50:09 +00:00

cudagraph_utils.py

[Bugfix][MRV2] Initialize DCP metadata after batch partitioning (#55212 )

2026-09-10 06:50:09 +00:00

dp_utils.py

[1/2][Model Runner V2] DBO support, eager mode (#50945 )

2026-09-04 14:17:39 -07:00

ec_connector.py

[EPD] Add ECMooncakeConnector for encoder cache over Mooncake TransferEngine (#41567 )

2026-09-07 06:21:43 +00:00

eplb_utils.py

[Elastic EP] Reduce eager-mode reconfiguration downtime (#51885 )

2026-08-19 02:13:06 +00:00

input_batch.py

[Core] MRV2 support for fast-prefill (#56145 )

2026-09-10 10:36:04 -07:00

kv_connector.py

[Core][KV Connector] Start async KV loads after the forward launch when no sync loads are scheduled (#53333 )

2026-08-28 21:58:00 +00:00

lora_utils.py

[BugFix][MRV2] Don't create dummy requests longer than max_model_len (#49751 )

2026-07-27 02:04:20 +00:00

model_runner.py

[Bugfix] Fall back to full decode graphs for noncompiled models (#55095 )

2026-09-11 01:56:05 -07:00

pcp_manager.py

[PCP][Spec Decode] Adds PCP support for single-module MTP and replicated DSpark. (#56107 )

2026-09-10 22:07:53 -07:00

pp_utils.py

[Bugfix][V2] record_stream idx_mapping in the PP draft broadcast (#55745 )

2026-09-09 12:55:56 -07:00

README.md

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

shutdown.py

[MRV2] Add shutdown() method (#41297 )

2026-05-02 21:06:30 -07:00

states.py

[Model Runner V2][Spec Decode] Add multi-layer MTP speculator (#48892 )

2026-07-30 15:54:15 -07:00

structured_outputs.py

[Bugfix][Spec Decode][Structured Output] DSpark: fix the grammar bitmask mapping when the draft budget is zero (#52436 )

2026-08-16 11:09:23 +00:00

ubatch_utils.py

[Core] MRV2 support for fast-prefill (#56145 )

2026-09-10 10:36:04 -07:00

warmup.py

[Bugfix] Defer adaptive verification until after kernel warmup (#55455 )

2026-09-06 11:31:40 -07:00

README.md

[Experimental] Model Runner V2

This directory contains the new model runner which is under active development. Ping Woosuk Kwon for any changes.