Commits

Branch selector

 main

User selector

robertgshaw2-neuralmagic

All time

Commit History

Commits on Dec 30, 2024

• [V1] [6/N] API Server: Better Shutdown (vllm-project#11586)

  robertgshaw2-neuralmagic

  authored
  5886aa4

Commits on Dec 28, 2024

• [V1] [5/N] API Server: unify Detokenizer and EngineCore input (vllm-project#11545)

  Show description for 4fb8e32
  robertgshaw2-neuralmagic

  authored
  4fb8e32

• [V1] [4/N] API Server: ZMQ/MP Utilities (vllm-project#11541)

  robertgshaw2-neuralmagic

  authored
  df04dff

Commits on Dec 27, 2024

• [BugFix] Fix quantization for all other methods (vllm-project#11547)

  robertgshaw2-neuralmagic

  authored
  2339d59

• [V1][3/N] API Server: Reduce Task Switching + Handle Abort Properly (vllm-project#11534)

  robertgshaw2-neuralmagic

  authored
  1b875a0

• [CI] Fix broken CI (vllm-project#11543)

  robertgshaw2-neuralmagic

  authored
  46d4359

• Update openai_compatible_server.md (vllm-project#11536)

  Show description for 0c0c201
  

  robertgshaw2-neuralmagic

  and

  simon-mo

  authored
  0c0c201

Commits on Dec 26, 2024

• [2/N] API Server: Avoid ulimit footgun (vllm-project#11530)

  robertgshaw2-neuralmagic

  authored
  55fb97f

• [1/N] API Server (Remove Proxy) (vllm-project#11529)

  robertgshaw2-neuralmagic

  authored
  720b10f

Commits on Nov 11, 2024

• [V1] AsyncLLM Implementation (vllm-project#9826)

  Show description for 6ace6fb
  

  4 peopleauthored
  6ace6fb

Commits on Nov 4, 2024

• [Bugfix] Fix MQLLMEngine hanging (vllm-project#9973)

  Show description for 04cef2c
  robertgshaw2-neuralmagic

  authored
  04cef2c

• [CI] Basic Integration Test For TPU (vllm-project#9968)

  Show description for 1c45f4c
  robertgshaw2-neuralmagic

  authored
  1c45f4c

• [V1] Fix Configs (vllm-project#9971)

  robertgshaw2-neuralmagic

  authored
  91c9ebb

Commits on Nov 2, 2024

• [V1] Fix EngineArgs refactor on V1 (vllm-project#9954)

  robertgshaw2-neuralmagic

  authored
  d6459b4

Commits on Oct 28, 2024

• Fix beam search eos (vllm-project#9627)

  robertgshaw2-neuralmagic

  authored
  feb92fb

Commits on Oct 17, 2024

• Support BERTModel (first encoder-only embedding model) (vllm-project#9056)

  Show description for 343f8e0
  

  6 peopleauthored
  343f8e0

Commits on Aug 31, 2024

• [BugFix][Core] Multistep Fix Crash on Request Cancellation (vllm-project#8059)

  robertgshaw2-neuralmagic

  authored
  8423aef

Commits on Aug 21, 2024

• [Frontend] Improve Startup Failure UX (vllm-project#7716)

  robertgshaw2-neuralmagic

  authored
  970dfdc

• [Bugfix][Frontend] Fix Issues Under High Load With zeromq Frontend (vllm-project#7394)

  Show description for f7e3b0c
  

  robertgshaw2-neuralmagic

  and

  njhill

  authored
  f7e3b0c

Commits on Aug 18, 2024

• [ Bugfix ] Fix Prometheus Metrics With zeromq Frontend (vllm-project#7279)

  Show description for e3b3182
  

  robertgshaw2-neuralmagic

  and

  njhill

  authored
  e3b3182

Commits on Aug 7, 2024

• [ BugFix ] Move zmq frontend to IPC instead of TCP (vllm-project#7222)

  robertgshaw2-neuralmagic

  authored
  5649857

Commits on Aug 6, 2024

• [ BugFix ] Fix ZMQ when VLLM_PORT is set (vllm-project#7205)

  robertgshaw2-neuralmagic

  authored
  541c185

Commits on Aug 3, 2024

• [ Frontend ] Multiprocessing for OpenAI Server with zeromq (vllm-project#6883)

  Show description for ed812a7
  

  4 peopleauthored
  ed812a7

Commits on Jul 25, 2024

• [ Misc ] fp8-marlin channelwise via compressed-tensors (vllm-project#6524)

  Show description for 889da13
  

  robertgshaw2-neuralmagic

  and

  mgoin

  authored
  889da13

Commits on Jul 20, 2024

• [ Bugfix ] Fix AutoFP8 fp8 marlin (vllm-project#6609)

  robertgshaw2-neuralmagic

  authored
  082ecd8

• [ Kernel ] Enable fp8-marlin for fbgemm-fp8 models (vllm-project#6606)

  robertgshaw2-neuralmagic

  authored
  9364f74

• [ Misc ] fbgemm checkpoints (vllm-project#6559)

  robertgshaw2-neuralmagic

  authored
  683e3cb

Commits on Jul 19, 2024

• [ Kernel ] Enable Dynamic Per Token fp8 (vllm-project#6547)

  robertgshaw2-neuralmagic

  authored
  4cc24f0

• [ Misc ] non-uniform quantization via compressed-tensors for Llama (vllm-project#6515)

  robertgshaw2-neuralmagic

  authored
  dbe5588

Commits on Jul 18, 2024

• [ Misc ] Improve Min Capability Checking in compressed-tensors (vllm-project#6522)

  robertgshaw2-neuralmagic

  authored
  58ca663

• [ Kernel ] Fp8 Channelwise Weight Support (vllm-project#6487)

  robertgshaw2-neuralmagic

  authored
  18fecc3

Commits on Jul 15, 2024

• [CI/Build] Cross python wheel (vllm-project#6394)

  robertgshaw2-neuralmagic

  authored
  a754dc2

Commits on Jul 14, 2024

• [ Misc ] Enable Quantizing All Layers of DeekSeekv2 (vllm-project#6423)

  robertgshaw2-neuralmagic

  authored
  73030b7

• [ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 (vllm-project#6417)

  robertgshaw2-neuralmagic

  authored
  fb6af8b

Commits on Jul 13, 2024

• [ Misc ] More Cleanup of Marlin (vllm-project#6359)

  Show description for babf52d
  robertgshaw2-neuralmagic

  authored
  babf52d

Pagination

PreviousNext