Ecosyste.ms: Timeline

Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.

sixsixcoder

sixsixcoder pushed 413 commits to cogagent sixsixcoder/vllm
  • [Model] Support `is_causal` HF config field for Qwen2 model (#10621) Signed-off-by: DarkLight1337 <tlleungac@connect... ed46f14
  • Super tiny little typo fix (#10633) 2b0879b
  • [Bug]: Authorization ignored when root_path is set (#10606) Signed-off-by: chaunceyjiang <[email protected]> d04b13a
  • [Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices (#9850) Signed-off-by: Wallas Santos <wallas... c27df94
  • [Docs] Add Snowflake Slides (#10641) Signed-off-by: simon-mo <[email protected]> 452a4e8
  • [Model]: Add support for Aria model (#10514) Signed-off-by: xffxff <[email protected]> Co-authored-by: Isotr0py <203... b1d9205
  • [Model] Enable optional prefix when loading embedding models (#10639) Signed-off-by: DarkLight1337 <tlleungac@connec... cf73f0c
  • [Doc] Fix typos in docs (#10636) Signed-off-by: DarkLight1337 <[email protected]> 1b583cf
  • [Model] Add OLMo November 2024 model (#10503) 9db713a
  • [misc] do not read HOST_IP (#10644) Signed-off-by: youkaichao <[email protected]> 6e9ff05
  • [bugfix] fix aria model and add torch.compile (#10645) Signed-off-by: youkaichao <[email protected]> 45ac4ff
  • [Feature] vLLM ARM Enablement for AARCH64 CPUs (#9228) Signed-off-by: Sanket Kale <[email protected]> Co-aut... a6760f6
  • [v1] EngineArgs for better config handling for v1 (#10382) Signed-off-by: rickyx <[email protected]> 519e8e4
  • custom allreduce + torch.compile (#10121) Signed-off-by: youkaichao <[email protected]> Co-authored-by: youkaich... 9a88f89
  • [Misc] Remove outdated init protocols (#10655) Signed-off-by: DarkLight1337 <[email protected]> 9406353
  • [ci] add vllm_test_utils (#10659) Signed-off-by: youkaichao <[email protected]> 334d64d
  • [V1] Enable profile for LLMEngine (#10665) 1f6584e
  • [Bugfix] Fix for Spec model TP + Chunked Prefill (#10232) Signed-off-by: andoorve <[email protected]... db66e01
  • [Hardware][NVIDIA] Add non-NVML CUDA mode for Jetson (#9735) Signed-off-by: Conroy Cheers <[email protected]> f5792c7
  • [Bugfix] Fix using `-O[0,3]` with LLM entrypoint (#10677) Signed-off-by: mgoin <[email protected]> 9a99273
  • and 393 more ...

View on GitHub

sixsixcoder created a branch on sixsixcoder/vllm

cogagent - A high-throughput and memory-efficient inference and serving engine for LLMs

sixsixcoder created a comment on an issue on THUDM/GLM-4-Voice
看样子您在mac M系列芯片上部署该模型，这个模型目前不支持在mac上部署

View on GitHub

sixsixcoder created a comment on an issue on THUDM/GLM-4-Voice
我们不提供safetensors如何转成whisper的bin结构，也不提供c++部署方式，该模型的基座是GLM-4模型，这个在网络上可能有相应的转换代码。

View on GitHub

sixsixcoder created a comment on an issue on THUDM/GLM-4-Voice
目前模型只支持较短的语音生成，可能对长语言生成能力有限

View on GitHub

sixsixcoder created a comment on an issue on THUDM/GLM-4-Voice
您可以在技术报告中找到答案 https://arxiv.org/abs/2412.02612

View on GitHub

sixsixcoder created a comment on an issue on THUDM/GLM-4-Voice
This is a good idea. Since we are using the GLM-4 base model, you can follow the technical report of GLM-4. GLM-4-voice should retain the basic capabilities of GLM-4 such as these languages

View on GitHub