Skip to content

OpenAI-compatible LLM inference simulator for xPyD — dummy prefill/decode nodes with realistic behavior

active 2026-04-042026-04-06 (UTC)

Complete coverage26,440 / 26,440 hourly files (100%) · 2 absent upstream2023-08-152026-08-20 (UTC)
Events
119
Pushes
40
Pull requests
17
Issues
23
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 3 days from 2026-04-04 to 2026-04-06. Pushes: 40 total, peak 16 in a day. Pull requests: 17 total, peak 7 in a day. Issues: 23 total, peak 15 in a day. Comments: 5 total, peak 2 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
hlin999140175
Copilot1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#85hlin992026-04-06 14:55
  • Pull request#84hlin992026-04-06 14:31
  • Releasehlin992026-04-06 04:28
    v0.4.0
  • Pull request#79hlin992026-04-06 01:21
  • Issue comment#79hlin992026-04-06 00:35
    feat: add tool calling support for vLLM compatibility
  • Issue comment#79hlin992026-04-05 16:25
    feat: add tool calling support for vLLM compatibility
  • Pull request#79hlin992026-04-05 16:10
  • Issue#75hlin992026-04-05 15:51
    Feature: 补齐 bench 兼容性缺口 — embeddings / tool calling / structured output / auth / gzip / 参数校验
  • Pull request#78hlin992026-04-05 15:51
  • Pull request#74hlin992026-04-05 12:07
  • Releasehlin992026-04-05 03:56
    v0.1.1
  • Pull request#69hlin992026-04-05 03:55
  • Issue#68hlin992026-04-05 03:13
    All DESIGN.md Constraints Successfully Verified (Observability, Mode, Configuration, Scheduling)
  • Pull request#66hlin992026-04-05 02:58
  • Issue comment#64hlin992026-04-05 02:56
    Batch Metrics and /debug/batch endpoint still missing/disabled
  • Issue#64hlin992026-04-05 02:49
    Batch Metrics and /debug/batch endpoint still missing/disabled
  • Issue#53hlin992026-04-05 02:19
    Bug: /v1/completions endpoint never enforces max_model_len
  • Issue#50hlin992026-04-05 02:19
    Bug: max_model_len not enforced in non-scheduled (legacy) mode
  • Issue#51hlin992026-04-05 02:19
    Bug: prefill/app.py missing /ping and /metrics endpoints
  • Issue#54hlin992026-04-05 02:19
    Bug: /v1/completions 端点在 scheduling 模式下未经过 Scheduler 处理
  • Issue#56hlin992026-04-05 02:19
    Bug: Warmup penalty 在 scheduling 模式下未生效
  • Issue#52hlin992026-04-05 02:19
    Bug: Warmup penalty not applied when scheduling is enabled
  • Issue#58hlin992026-04-05 02:19
    Bug: Scheduler _form_prefill_batch still crashes outside async context after #32 fix
  • Pull request#59hlin992026-04-05 02:19
  • Issue#60hlin992026-04-05 01:53
    Implementation deviates from DESIGN.md: Mode Switching, Configuration, and Observability broken

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.