Commits

Branch selector

 main

User selector

robertgshaw2-redhat

Datepicker

All time

Commit History

Commits on Aug 7, 2024

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

  robertgshaw2-redhat

  authored
  5649857

  Copy full SHA for 5649857

Commits on Aug 6, 2024

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

  robertgshaw2-redhat

  authored
  541c185

  Copy full SHA for 541c185

Commits on Aug 3, 2024

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

  Show description for ed812a7
  

  4 peopleauthored
  ed812a7

  Copy full SHA for ed812a7

Commits on Jul 25, 2024

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

  Show description for 889da13
  

  robertgshaw2-redhat

  and

  mgoin

  authored
  889da13

  Copy full SHA for 889da13

Commits on Jul 20, 2024

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

  robertgshaw2-redhat

  authored
  082ecd8

  Copy full SHA for 082ecd8

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

  robertgshaw2-redhat

  authored
  9364f74

  Copy full SHA for 9364f74

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

  robertgshaw2-redhat

  authored
  683e3cb

  Copy full SHA for 683e3cb

Commits on Jul 19, 2024

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

  robertgshaw2-redhat

  authored
  4cc24f0

  Copy full SHA for 4cc24f0

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

  robertgshaw2-redhat

  authored
  dbe5588

  Copy full SHA for dbe5588

Commits on Jul 18, 2024

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

  robertgshaw2-redhat

  authored
  58ca663

  Copy full SHA for 58ca663

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

  robertgshaw2-redhat

  authored
  18fecc3

  Copy full SHA for 18fecc3

Commits on Jul 15, 2024

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

  robertgshaw2-redhat

  authored
  a754dc2

  Copy full SHA for a754dc2

Commits on Jul 14, 2024

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

  robertgshaw2-redhat

  authored
  73030b7

  Copy full SHA for 73030b7

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

  robertgshaw2-redhat

  authored
  fb6af8b

  Copy full SHA for fb6af8b

Commits on Jul 13, 2024

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

  Show description for babf52d
  robertgshaw2-redhat

  authored
  babf52d

  Copy full SHA for babf52d

Commits on Jul 12, 2024

• [ Misc ] Support Models With Bias in compressed-tensors integration (vllm-project#6356)

  robertgshaw2-redhat

  authored
  aea19f0

  Copy full SHA for aea19f0

• [ Misc ] Remove separate bias add (vllm-project#6353)

  robertgshaw2-redhat

  authored
  6047187

  Copy full SHA for 6047187

Commits on Jul 11, 2024

• [ BugFix ] Prompt Logprobs Detokenization (vllm-project#6223)

  Show description for 7ed6a4f
  

  robertgshaw2-redhat

  and

  zifeitong

  authored
  7ed6a4f

  Copy full SHA for 7ed6a4f

• [ Misc ] Refactor Marlin Python Utilities (vllm-project#6082)

  Show description for b675069
  robertgshaw2-redhat

  authored
  b675069

  Copy full SHA for b675069

Commits on Jul 7, 2024

• [ Misc ] Support Fp8 via llm-compressor (vllm-project#6110)

  Show description for abfe705
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  abfe705

  Copy full SHA for abfe705

Commits on Jul 3, 2024

• [ Misc ] Clean Up CompressedTensorsW8A8 (vllm-project#6113)

  robertgshaw2-redhat

  authored
  62963d1

  Copy full SHA for 62963d1

Commits on Jul 2, 2024

• [ Misc ] Refactor MoE to isolate Fp8 From Mixtral (vllm-project#5970)

  Show description for 7c008c5
  

  3 peopleauthored
  7c008c5

  Copy full SHA for 7c008c5

• Update conftest.py (vllm-project#6076)

  robertgshaw2-redhat

  authored
  4d26d80

  Copy full SHA for 4d26d80

Commits on Jul 1, 2024

• [ CI ] Re-enable Large Model LM Eval (vllm-project#6031)

  robertgshaw2-redhat

  authored
  d76084c

  Copy full SHA for d76084c

Commits on Jun 30, 2024

• [ Misc ] Refactor w8a8 to use process_weights_after_load (Simplify Weight Loading) (vllm-project#5940)

  Show description for af9ad46
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  af9ad46

  Copy full SHA for af9ad46

• [ CI ] Temporarily Disable Large LM-Eval Tests (vllm-project#6005)

  Show description for deacb7e
  

  robertgshaw2-redhat

  and

  [email protected]

  authored
  deacb7e

  Copy full SHA for deacb7e

Commits on Jun 29, 2024

• [ CI/Build ] LM Eval Harness Based CI Testing (vllm-project#5838)

  Show description for 75aa144
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  75aa144

  Copy full SHA for 75aa144

• [ CI/Build ] Added E2E Test For Compressed Tensors (vllm-project#5839)

  Show description for 8dbfcd3
  

  3 peopleauthored
  8dbfcd3

  Copy full SHA for 8dbfcd3

Commits on Jun 28, 2024

• [Bugfix] Fix Engine Failing After Invalid Request - AsyncEngineDeadError (vllm-project#5963)

  Show description for 6a62cb8
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  6a62cb8

  Copy full SHA for 6a62cb8

• [ Bugfix ] Enabling Loading Models With Fused QKV/MLP on Disk with FP8 (vllm-project#5921)

  Show description for 2cd402e
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  2cd402e

  Copy full SHA for 2cd402e

• [ Misc ] Remove fp8_shard_indexer from Col/Row Parallel Linear (Simplify Weight Loading) (vllm-project#5928)

  Show description for b185230
  

  robertgshaw2-redhat

  and

  Robert Shaw

  authored
  b185230

  Copy full SHA for b185230

Commits on Jun 14, 2024

• [ Misc ] Rs/compressed tensors cleanup (vllm-project#5432)

  Show description for 1598568
  

  3 peopleauthored
  1598568

  Copy full SHA for 1598568

Commits on Jun 1, 2024

• [BugFix] Prevent LLM.encode for non-generation Models (vllm-project#5184)

  Show description for 044793d
  

  robertgshaw2-redhat

  and

  mgoin

  authored
  044793d

  Copy full SHA for 044793d

Commits on May 31, 2024

• [Bugfix] Avoid Warnings in SparseML Activation Quantization (vllm-project#5120)

  robertgshaw2-redhat

  authored
  b35be54

  Copy full SHA for b35be54

Commits on May 30, 2024

• [Bugfix] Automatically Detect SparseML models (vllm-project#5119)

  robertgshaw2-redhat

  authored
  d910816

  Copy full SHA for d910816

Pagination

Previous

Next