Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

vLLM
docs.vllm.ai > projects > vllm-omni > en > latest > user_guide > quantization > fp8

FP8 W8A8 - vLLM-Omni

2+ mon, 3+ week ago   (218+ words) FP8 quantization converts BF16/FP16 weights to FP8 at model load time. Online activation scaling is the default and does not require calibration. Static activation scaling is supported when calibrated scale information is available. For ModelOpt-produced pre-quantized checkpoints, see ModelOpt Quantization. Some architectures can…...

vLLM
docs.vllm.ai > en > latest > design > attention_backends

Attention Backend Feature Support

5+ mon, 3+ week ago   (268+ words) Do not edit this file manually. Run the following command to regenerate it: There are two ways to specify the backend from the command line: Note: --attention-backend and --attention-config.backend are mutually exclusive. Use one or the other, not both....

vLLM
docs.vllm.ai > projects > ascend > en > v0.23.0 > developer_guide > performance_and_debug > optimization_and_tuning.html

Optimization and Tuning

4+ day, 22+ hour ago   (504+ words) This guide aims to help users improve vLLM Ascend performance at the system level. It includes OS configuration, library optimization, deployment guide, and so on. Any feedback is welcome. Install vLLM and vLLM Ascend: Please follow the Installation Guide to…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling

inkling

6+ day, 3+ hour ago   (92+ words) vLLM Inkling model configs for the text backbone and audio/vision towers. NVFP4 (ModelOpt) support for the Inkling mixture-of-experts. Text-only entry point ( inkling_model checkpoints). Top-level (multimodal) entry point. Bases: _TmlForCausalLMBase, SupportsMultiModal Builds the vision + audio towers on top of the shared text backbone....

vLLM
docs.vllm.ai > en > latest > api > vllm > model_executor > layers > fused_moe > router > bf16x3_router_gemm_cutedsl

bf16x3_router_gemm_cutedsl

6+ day, 1+ hour ago   (64+ words) vLLM CuteDSL BF16x3 router GEMM. Computes X @ W.T for BF16 X with shape [N, K] and FP32 router weights W with shape [M, K] by decomposing each FP32 weight value into three BF16 residual terms inside the kernel, then accumulating the three BF16 MMA results into…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling > nvidia > attention

attention

6+ day, 3+ hour ago   (13+ words) vLLM Project the per-head relative branch r to per-distance logits....

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling > nvidia > ops > fa4_rel_attention

fa4_rel_attention

6+ day, 3+ hour ago   (82+ words) vLLM Round the FA4 scheduling bound up to a power of two. Return the split-KV cap for FA4 with sheared relative bias. Paged varlen FA4 over the bound K/V cache with the Inkling relative bias. q is (num_tokens, num_heads, head_dim); key_cache / value_cache are the paged caches (num_blocks, block_size, num_kv_heads, head_dim); block_table is…...

vLLM
docs.vllm.ai > en > latest > api > vllm > distributed > kv_transfer > kv_connector > v1 > offloading > config

config

5+ day, 23+ hour ago   (30+ words) vLLM Translate vLLM KV cache metadata for native offloading backends. Translate vLLM configuration into the native offloading boundary. Return whether a KV cache tensor uses a packed block stride....

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling > nvidia > ops > mm_towers

mm_towers

6+ day, 3+ hour ago   (77+ words) vLLM Fused CUDA kernels for the Inkling vision/audio towers. Both kernels keep the reference paths' fp32 accumulation and per-op bf16 rounding points (native rms_norm / F.gelu ); outputs are frequently bit-identical and otherwise differ by 1-2 bf16 ulps from reduction-order (real-checkpoint-weight cosine vs reference > 0.9999998). Fused gelu…...

vLLM
docs.vllm.ai > en > latest > api > vllm > models > inkling > nvidia > ops > norm

norm

6+ day, 2+ hour ago   (42+ words) vLLM Fused res = residual + delta; y = rmsnorm(res). Fused rmsnorm(embed_table[input_ids], weight) row gather + norm. add_rmsnorm(residual, delta, weight, eps) ¶ Returns (y, res); both are fresh tensors (cudagraph-friendly, no in-place update of the inputs)....