Matching posts

Matching terms are highlighted

POST

User reports DeepSeek V4.1 Flash 1017 takes ~65 minutes per run on vLLM

…work machine takes about 65 minutes, and notes vLLM is fast because it tunes for the GPU and precom…

deepseek-v4.1@Seb_Gode　Filed in No.020

1 day agoCopy original

LLM Gateway 24h token chart: V4.1 Flash builds flat but hold 55.7%

Three of LLM Gateway's top six models roughly tripled tokens…

deepseek-v4.1@LLMDevPass　Filed in No.020

23 hours agoCopy original

POST

Deployment: DeepSeek V4.1 Flash fails to start on 4x RTX 6000 Pro in mainline vLLM

A user complains vLLM merges PRs for non-mainstream setups too slowly…

deepseek-v4.1@Seb_Gode　Filed in No.020

19 hours agoCopy original

Which metric actually matters when comparing LLMs like DeepSeek V4.1

LLM modellerini karşılaştırırken yanlış metriğe bak…

deepseek-v4.1@TugserOkur　Filed in No.020

21 hours agoCopy original

DeepMedChem LLM suite ships ChatGPT plugin and MCP server

DeepMedChem released an LLM suite with official ChatGPT and Claude plugins,…

mcp@miroslavlzicar　Filed in No.014

23 hours agoCopy original

Jev-style scoring vs LLM decoding vs structured output for fixed-choice decisions

Jev-style scoring vs. LLM decoding vs. structured output, clearly explain…

jev@DailyDoseOfDS_　Filed in No.006

23 hours agoCopy original

POST

Local LLM roundup: V4.1 Flash called the strongest locally runnable model

A Japanese user weighs cloud vs local LLMs, notes Qwen3.8-Flash-Next and GLM-5.3-Flash hi…

deepseek-v4.1@UtaAoya　Filed in No.020

2 days agoCopy original

vLLM DEP32 vs DeepInfer: decoding benchmark on DeepSeek V4.1 Flash 1017

The community ran a head-to-head benchmark of vLLM DEP32 against DeepSeek's in-house DeepInfer fra…

deepseek-v4.1@DeepSeek_club　Filed in No.020

2 days agoCopy original

POST

DeepSeek V4.1 Flash on vLLM: sleep scheduling on a GB300

…added wait 1.3 s Model: DeepSeek V4.1 Flash on vLLM. Sleeps in ~10 s, wakes in ~2.5 s.

deepseek-v4.1@benbuschmann　Filed in No.020

1 day agoCopy original

POST

Export bans fueled local LLM renaissance; DeepSeek V4.1 Flash 1017 runs on 4 DGX Spark at home

…cess to. which lead to the renaissance of local llm. take deepseek v4.1 flash 1017 for example, the…

deepseek-v4.1@zengjiajun_eth　Filed in No.020

1 day agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.