github.com Sep 09
GitHub - ciprianveg/3090-vllm:
Contribute to ciprianveg/3090-vllm development by creating an account on GitHub.
github.com/ciprianveg/3090-vllm
Story Details
| Last Updated | |
| Total Articles | 1 |
Main Topics
Similar to This
Previous
github.com 5h
Enable Qwen3.8-flash-next 8 cards fp8 & int4 and optimize qwen4-27b by hzjane · Pull Request #22 · analytics-zoo/vllm-xpu-kernels
github.com/analytics-zoo/vllm-xpu-kernels/pull/22
github.com Oct 21
GitHub - Zagitta/gpu-unlock: Contribute to Zagitta/gpu-unlock development by creating an account on GitHub.
github.com/Zagitta/gpu-unlock
github.com Oct 17
B70_Quad/qfn-38-fp8-4xb70-mtp at master · wormley/B70_Quad: Recipes For LLMs on 4x Intel Arc B70 Cards. Contribute to wormley/B70_Quad development by creating an ...
github.com/wormley/B70_Quad/tree/master/qfn-38-fp8-4xb70-mtp
github.com Oct 10
GitHub - weicj/vLLM-2080Ti-Definitive: The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ ...
github.com/weicj/vLLM-2080Ti-Definitive
github.com Sep 19
club-3090/docs/MULTI_CARD.md at master · noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp ...
github.com/noonghunna/club-3090/blob/master/docs/MULTI_CARD.md
github.com Aug 30
GitHub - dysangel/vllm at qwen38next-sm121: A high-throughput and memory-efficient inference and serving engine for LLMs - GitHub - dysangel/vllm at ...
github.com/dysangel/vllm/tree/qwen38next-sm121
github.com Aug 19
GitHub - uraniumchonk/vllm-hybrid-mamba-notes: Field notes: vLLM + hybrid Mamba/GDN + MTP + LMCache. Version matrix, symptoms, and the prefix-hit failure mode.
github.com/uraniumchonk/vllm-hybrid-mamba-notes
github.com Aug 15
GitHub - syv-ai/qwen38-27b-rtx3090: Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state) ...
github.com/syv-ai/qwen38-27b-rtx3090
github.com Aug 11
GitHub - raullenchai/twinspark: Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster ...
github.com/raullenchai/twinspark
github.com Jul 21
GitHub - oteomamo/SALT: Salience-aware lexical trie for long-context compression.
github.com/oteomamo/SALT
github.com Jul 14
GitHub - ciprianveg/gb10-glm-5.2: GLM-5.2-Int4-Int8 on 8x GB10 cluster: GLM-5.2-Int4-Int8 on 8x GB10 cluster. Contribute to ciprianveg/gb10-glm-5 ...
github.com/ciprianveg/gb10-glm-5.2
github.com Jun 08
club-3090/models/qwen3.6-27b/vllm/compose/dual/fp8/mtp.yml at master · noonghunna/club-3090
github.com/noonghunna/club-3090/blob/master/models/qwen3.6-27b/vllm/compose/dual/fp8/mtp.yml
github.com Jun 02
club-3090/models/qwen3.6-27b/vllm/compose/dual/carnice-bf16mtp/bf16-mtp.yml at master · noonghunna/club-3090
github.com/noonghunna/club-3090/blob/master/models/qwen3.6-27b/vllm/compose/dual/carnice-bf16mtp/bf16-mtp.yml
github.com Apr 27
GitHub - tedivm/qwen36-27b-docker: vLLM Docker Container for Qwen36 27b: vLLM Docker Container for Qwen36 27b. Contribute to tedivm/qwen36-27b-docker development ...
github.com/tedivm/qwen36-27b-docker
github.com Apr 14
GitHub - jungledesh/profile: A physics-grounded, cost-aware optimizer for vLLM.: A physics-grounded, cost-aware optimizer for vLLM. - jungledesh/profile
github.com/jungledesh/profile
github.com Apr 06
GitHub - ai-infos/vllm-gfx906-mobydick: A high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g ...
github.com/ai-infos/vllm-gfx906-mobydick
github.com Mar 29
GitHub - namake-taro/vllm-custom: Contribute to namake-taro/vllm-custom development by creating an account on GitHub.
github.com/namake-taro/vllm-custom
github.com Mar 28
GitHub - Jransom33/Chatterbox-turbo-vllm: VLLM Port of the Chatterbox Turbo TTS model
github.com/Jransom33/Chatterbox-turbo-vllm
github.com Mar 08
GitHub - uaysk/vllm-pascal: vLLM fork for pascal gpu: vLLM fork for pascal gpu. Contribute to uaysk/vllm-pascal development by creating an account on GitHub.
github.com/uaysk/vllm-pascal
Next