MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
active 2025-02-03 → 2026-04-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 425 days from 2025-02-03 to 2026-04-03. Pushes: 36 total, peak 11 in a day. Pull requests: 17 total, peak 5 in a day. Issues: 10 total, peak 2 in a day. Comments: 13 total, peak 2 in a day. Stars: 125 total, peak 4 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| loadams | 55 | 34 | 14 | 3 |
| Flink-ddd | 4 | 0 | 0 | 4 |
| tohtana | 3 | 1 | 1 | 1 |
| tjruwase | 3 | 1 | 0 | 0 |
| tishizaki | 2 | 0 | 1 | 0 |
| vitali87 | 1 | 0 | 1 | 0 |
| nouf01 | 1 | 0 | 0 | 1 |
| npdev1 | 1 | 0 | 0 | 1 |
| Sptbr | 1 | 0 | 0 | 1 |
| besrym | 1 | 0 | 0 | 1 |
| Dragon-Wu | 1 | 0 | 0 | 1 |
| sfc-gh-mwyatt | 1 | 0 | 0 | 0 |
| paprika0741 | 1 | 0 | 0 | 0 |
| impacterai | 1 | 0 | 0 | 0 |
| KMouratidis | 1 | 0 | 0 | 0 |
| yangzhch6 | 1 | 0 | 0 | 0 |
| InderjeetVishnoi | 1 | 0 | 0 | 0 |
| dgzxx-2000 | 1 | 0 | 0 | 0 |
| riedgar-ms | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#570impacterai2026-04-03 22:05Add Repurpose AI — AI content repurposing tool
- Pull request#569vitali872026-03-22 14:37
- Issue#406yangzhch62025-10-05 11:22How to generate multiple responses in one time?
- Issue comment#545npdev12025-08-14 12:38Issue: Multi-node and Multi-GPU Inference Problems with DeepSpeed MII
- Issue comment#513Sptbr2025-08-11 14:25non-persistent example doesn't work on Mixtral-8*7B-v0.1
- Issue#568InderjeetVishnoi2025-07-02 08:32**Issue with Dockerized DeepSpeed-MII Persistent Deployment (LLama 3 70B Model) – Tensor Parallelism Not Effective**
- Issue comment#567Flink-ddd2025-07-01 00:25fix(setup): Explicitly include 'mii' package in find_packages
- Pull request#567tohtana2025-06-30 16:21
- Issue comment#567Flink-ddd2025-06-28 02:05fix(setup): Explicitly include 'mii' package in find_packages
- Issue comment#567Flink-ddd2025-06-26 04:32fix(setup): Explicitly include 'mii' package in find_packages
- Issue comment#567Flink-ddd2025-06-25 01:25fix(setup): Explicitly include 'mii' package in find_packages
- Issue comment#567tohtana2025-06-24 22:13fix(setup): Explicitly include 'mii' package in find_packages
- Issue#566dgzxx-20002025-05-14 13:52ValueError: Unsupported model type qwen3
- Issue#565paprika07412025-05-12 15:48Question: Is Expert Parallelism Supported?
- Issue comment#521besrym2025-04-17 07:25OpenAI server fails
- Issue comment#521nouf012025-04-08 23:53OpenAI server fails
- Pull request#564loadams2025-03-25 20:04
- Pull request#564loadams2025-03-25 19:50
- Releaseloadams2025-03-25 19:50v0.3.3
- Pull request#563loadams2025-03-25 18:43
- Pull request#562loadams2025-03-25 16:39
- Pull request#562loadams2025-03-25 15:59
- Pull request#561loadams2025-03-24 21:26
- Issue#548loadams2025-03-24 21:15persistent deployment (qwen2-7b-instruct) model responds abnormally
- Pull request#561loadams2025-03-24 21:02
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 125 stars here means stars gained during the window, not the repo's star count.