liuchenbing2026andliuchenbing f6983f01de MiniMax-M2: add Eagle3 speculative decoding support (#37512) ...

Signed-off-by: liuchenbing <chenliumail@163.com>
Signed-off-by: liucb <liuchengbao_work@163.com>
Co-authored-by: liuchenbing <chenliumail@163.com>

2026-04-05 19:50:18 -07:00

..

__init__.py

[Feature] limit thinking tokens (hard limit) (#20859)

2026-03-24 09:53:07 -07:00

attention.py

[Bugfix][MLA] Change default SM100 MLA prefill backend back to TRT-LLM (#38562)

2026-03-30 09:51:24 -07:00

cache.py

[Feature] KV cache per-token-head INT8/FP8 quantization (#38378)

2026-04-02 08:13:26 -04:00

compilation.py

[mla] Support fused FP8/NVFP4 output quantization in MLA attention (#35792) (#36205)

2026-04-02 21:16:11 -04:00

device.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

ec_transfer.py

[Misc] Introduce ec_both role EC (encoder cache) connector (#34182)

2026-02-10 18:55:35 +00:00

kernel.py

[vLLM IR] add import_ir_kernels() to support OOT platforms (#38807)

2026-04-03 17:25:19 +00:00

kv_events.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

kv_transfer.py

[Misc] Set default kv_buffer_device in a better way (#36862)

2026-03-13 19:07:33 +00:00

load.py

Remove need for explicit \n in docstring lists for --help formatting (#38350)

2026-03-27 08:38:00 -07:00

lora.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

model_arch.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

model.py

[Quantization][Deprecation] Remove Petit NVFP4 (#32694)

2026-04-05 00:07:45 +00:00

multimodal.py

Remove need for explicit \n in docstring lists for --help formatting (#38350)

2026-03-27 08:38:00 -07:00

observability.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

offload.py

[offloader] v2: Hide weight onloading latency via prefetching (#29941)

2026-02-25 17:20:59 -08:00

parallel.py

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

pooler.py

[Deprecate] Deprecate pooling multi task support. (#37956)

2026-03-24 14:07:47 +00:00

profiler.py

Remove need for explicit \n in docstring lists for --help formatting (#38350)

2026-03-27 08:38:00 -07:00

quantization.py

[Frontend] new online quantization frontend (#38138)

2026-04-03 11:58:39 -04:00

reasoning.py

[Misc] Rename think_start_str/think_end_str to reasoning_start_str/reasoning_end_str (#38242)

2026-04-01 09:56:45 -07:00

scheduler.py

Remove need for explicit \n in docstring lists for --help formatting (#38350)

2026-03-27 08:38:00 -07:00

speculative.py

MiniMax-M2: add Eagle3 speculative decoding support (#37512)

2026-04-05 19:50:18 -07:00

speech_to_text.py

[MM] Allow audio chunking for offline LLM (#34628)

2026-02-23 21:04:28 -08:00

structured_outputs.py

Remove unused disable_fallback field (#36546)

2026-03-09 20:56:54 -07:00

utils.py

Remove need for explicit \n in docstring lists for --help formatting (#38350)

2026-03-27 08:38:00 -07:00

vllm.py

[Model Runner V2] Add config validation for not-yet-supported features (#38758)

2026-04-03 12:08:08 -07:00

weight_transfer.py

[Feat][RL][2/2] Native Weight Syncing API: IPC (#34171)

2026-02-27 13:45:21 -07:00