|
About the Features category
|
|
0
|
149
|
March 20, 2025
|
|
Allow agent to change speculative_tokens in each request
|
|
1
|
81
|
September 24, 2026
|
|
Decode KV writeback: can multi-turn chat preserve cache reuse with default templates?
|
|
1
|
101
|
September 10, 2026
|
|
vLLM TurboQuant Implementation
|
|
1
|
93
|
September 7, 2026
|
|
Customize prefix caching
|
|
1
|
133
|
August 9, 2026
|
|
Sparse attention (e.g., H2O)
|
|
2
|
296
|
July 1, 2026
|
|
Is there a hook/flag to capture activation statistics during inference for use with llm-compressor AWQ?
|
|
3
|
140
|
June 4, 2026
|
|
Dose vllm support Qwen3.5 pd disaggregation with Mooncake?
|
|
1
|
191
|
May 28, 2026
|
|
Why Does Decode Forward on PP Stage 0 Appear to Precede Prefill Forward on PP Stage 1 for the Same Request?
|
|
1
|
64
|
May 26, 2026
|
|
GPTQModel 能量化 GLM-5 FP16 到 INT8 吗
|
|
9
|
311
|
April 24, 2026
|
|
DeepSeek MTP full cuda graph support?
|
|
3
|
269
|
April 13, 2026
|
|
Qwen3.5-27B-FP8 Speculative Decoding
|
|
2
|
2641
|
April 11, 2026
|
|
thinking_token_budget silently ignored when passed via extra_args in vLLM 0.18.0
|
|
1
|
1049
|
April 11, 2026
|
|
GLM 5 / Kimi k2.5 on 4 x RTX 6000 Pro
|
|
1
|
578
|
March 22, 2026
|
|
Compressed Multimodal embeddings inputs
|
|
1
|
102
|
March 18, 2026
|
|
NVFP4 Support In Attention
|
|
1
|
1674
|
March 16, 2026
|
|
Distributed Speculative Decoding using Ray
|
|
3
|
324
|
February 11, 2026
|
|
Deployment example for a qwen3 model with hybrid thinking
|
|
10
|
2947
|
February 4, 2026
|
|
How do I precompute multimodal embeddings?
|
|
5
|
795
|
February 2, 2026
|
|
Implementing hidden state probes
|
|
1
|
140
|
January 30, 2026
|
|
Standalone draft model spec decode support in v0.x and v1
|
|
3
|
419
|
January 20, 2026
|
|
How to get kv cache value from vllm
|
|
5
|
602
|
January 19, 2026
|
|
Is there a plan for EVS to support Qwen3VL in response to the issue of sparse video tokens?
|
|
1
|
205
|
January 13, 2026
|
|
Exposing KV cache for recomposition / reuse beyond prefix caching?
|
|
1
|
323
|
January 13, 2026
|
|
Why I feel cuda-kernel marlin run not fast?
|
|
5
|
515
|
January 9, 2026
|
|
Can reasoning_effort parameter not ne used in vllm implementation via python?
|
|
1
|
798
|
January 2, 2026
|
|
Understanding vllm kv cache
|
|
5
|
2973
|
December 1, 2025
|
|
Has anyone successfully run DBO in a single node multi card environment?
|
|
1
|
182
|
December 1, 2025
|
|
EPLB behavior in elastic scaling
|
|
21
|
617
|
November 28, 2025
|
|
Qwen2.5 VL开启flashinfer失败
|
|
5
|
554
|
November 24, 2025
|