Large Language Model Text Generation Inference
active 2025-03-25 → 2026-05-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 417 days from 2025-03-25 to 2026-05-15. Pushes: 82 total, peak 5 in a day. Pull requests: 82 total, peak 4 in a day. Issues: 40 total, peak 3 in a day. Comments: 137 total, peak 6 in a day. Stars: 442 total, peak 6 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 |
|---|---|---|---|---|
| regisss | 69 | 21 | 16 | 10 |
| sywangyi | 58 | 0 | 19 | 35 |
| drbh | 27 | 15 | 8 | 1 |
| dacorvo | 23 | 14 | 5 | 2 |
| Narsil | 22 | 7 | 6 | 3 |
| yuanwu2017 | 21 | 0 | 6 | 13 |
| danieldk | 17 | 10 | 2 | 1 |
| mht-sharma | 6 | 3 | 2 | 0 |
| MrExplode | 6 | 0 | 0 | 2 |
| tengomucho | 5 | 3 | 2 | 0 |
| MohannadEhabBarakat | 5 | 0 | 0 | 5 |
| HuggingFaceDocBuilderDev | 5 | 0 | 0 | 5 |
| alexshtf | 5 | 0 | 0 | 3 |
| jimburtoft | 4 | 0 | 0 | 3 |
| daniau23 | 4 | 0 | 0 | 1 |
| baughmann | 3 | 0 | 0 | 2 |
| fank | 3 | 0 | 0 | 3 |
| amadhan882 | 3 | 0 | 0 | 0 |
| baptistecolle | 3 | 3 | 0 | 0 |
| Akhil-ender | 3 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#3358BromigoTools2026-03-14 21:39Expose optional intermediate hidden states / layer logits during generation (for reasoning metrics and model introspection)
- Issue#3357prane-eth2026-03-14 12:10Feature Request: Add `action_guard` Parameter for centralized validation of agent tool calls
- Issue comment#3352julien-c2026-03-07 09:50docs: add AWS (EC2/SageMaker) deployment + benchmarking guide
- Issue#3355amadhan8822026-02-09 11:57Performance: Replace inefficient polling in server loop with event-driven shutdown and optimize Health check
- Pull request#3352KOKOSde2026-01-31 06:43
- Issue comment#78niguowei442026-01-21 05:25ModuleNotFoundError: No module named 'generate_pb2'
- Issue#3351StanByriukov022026-01-09 17:50KV-cache / long-context: smallest canonical repro boundary + metric (7-day receipts eval)
- Issue#3350PurpleSquirrelMedia2026-01-07 23:58[Feature Request] MCP Server for AI-Powered Model Development
- Pull request#3348salmanmkc2025-12-20 23:42
- Releasedrbh2025-12-19 14:35v3.3.7
- Issue comment#3344murphyslaw91882025-12-11 13:52Maintenance mode
- Pull request#3341Edge-Seven2025-11-18 07:33
- Issue#3336lingdoc2025-10-30 14:10Get inference endpoint model settings via client
- Issue comment#3333danieldk2025-09-29 11:52How to use prefix caching
- Pull request#3334htiennv2025-09-28 13:37
- Issue comment#2783fank2025-09-23 03:33"sharded is not supported for AutoModel" Error When Deploying SageMaker Endpoint For Qwen 2.5 7B Trained via SageMaker
- Issue comment#3247fank2025-09-22 15:55Load Chat Template from `chat_template.jinja`
- Issue comment#2676fank2025-09-22 11:36PREFIX_CACHING=0 does not disable prefix caching in v2.3.1
- Releasedrbh2025-09-17 00:48v3.3.6
- Pull request#3329drbh2025-09-16 23:15
- Issue comment#3296MohannadEhabBarakat2025-09-16 12:46tensorrt not running
- Pull request#3326drbh2025-09-09 14:44
- Pull request#3327julien-c2025-09-09 13:36
- Issue comment#3327HuggingFaceDocBuilderDev2025-09-09 13:17Update iframe sources for streaming demo
- Pull request#3327coyotte5082025-09-09 13:15
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 442 stars here means stars gained during the window, not the repo's star count.