Bole: Efficient Tree Speculation for Hybrid-Attention Language Models | Paper Citation Record

Observation 6329b19f-2260-42fd-b9bf-2ab9f8c1b84a · outbound

This paper cites Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.124106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9c3e815c-d5ac-46f1-91fd-671471c8f9f9 · outbound

This paper cites Open-swe-traces: Advancing dual-mode multilingual distillation for software engineering agents,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Open-swe-traces: Advancing dual-mode multilingual distillation for software engineering agents,

Reference 2

Resolution: verified exact; raw_fallback, observed 2026-08-04T23:34:57.854572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b358d3a9-81ac-414e-9fe2-f908aaa5f5a0 · outbound

This paper cites Program Synthesis with Large Language Models.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Program Synthesis with Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.701873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2d1821c-8c83-48db-91bd-4d22083b50dd · outbound

This paper cites Medusa: Simple LLM inference acceleration framework with multiple decoding heads,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Medusa: Simple LLM inference acceleration framework with multiple decoding heads,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.116183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5d56c3e1-8fa1-4da9-a50a-4006741a1276 · outbound

This paper cites Accelerating large language model decoding with speculative sampling,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Accelerating large language model decoding with speculative sampling,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.108000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 41c3e34a-2038-4378-b496-0fa3be60e862 · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.714038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a81927f-d5c7-4993-a494-1ce773e71ff2 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.717585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 296a7cc9-540f-4ea6-8f4a-de259765a09a · outbound

This paper cites Better & faster large language models via multi-token prediction,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Better & faster large language models via multi-token prediction,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.099691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f03a369e-2f3c-4956-b816-dc933ee702c4 · outbound

This paper cites Yggdrasil: Bridging dynamic speculation and static runtime for latency-optimal tree- based LLM decoding,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Yggdrasil: Bridging dynamic speculation and static runtime for latency-optimal tree- based LLM decoding,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.092451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94009cd4-5c80-4777-aab6-25484e9187ca · outbound

This paper cites Papi: Exploiting dynamic parallelism in large language model decoding with a processing-in-memory-enabled computing system,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Papi: Exploiting dynamic parallelism in large language model decoding with a processing-in-memory-enabled computing system,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.726380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d65ce328-f1ed-48ce-9452-d1ba3ef61784 · outbound

This paper cites Bridging draft policy misalignment: Group tree optimization for speculative decoding,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Bridging draft policy misalignment: Group tree optimization for speculative decoding,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.084724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fa33ab29-b983-483f-aaff-9bd1176265f0 · outbound

This paper cites Pod-attention: Unlocking full prefill-decode overlap for faster llm inference,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Pod-attention: Unlocking full prefill-decode overlap for faster llm inference,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.734525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 819522c8-b345-4da7-b4b4-19d448e8f0f9 · outbound

This paper cites Pimba: A processing-in-memory acceleration for post-transformer large language model serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Pimba: A processing-in-memory acceleration for post-transformer large language model serving,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.737160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b98fde6-42c6-4d26-b3d5-2e0de4616326 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Efficient memory management for large language model serving with pagedattention,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.739878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a41fce-23c2-4e55-a210-5bfde570bdf1 · outbound

This paper cites Fast inference from transformers via speculative decoding,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Fast inference from transformers via speculative decoding,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.076505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 510c84a3-2a10-4a5c-8067-64be9b2152fd · outbound

This paper cites Orches: Orchestrated test-time-compute-based llm reasoning on collaborative gpu-pim heterogeneous system,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Orches: Orchestrated test-time-compute-based llm reasoning on collaborative gpu-pim heterogeneous system,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.748666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8490ba93-2d01-485a-a550-cf3627768e51 · outbound

This paper cites EAGLE-2: Faster inference of language models with dynamic draft trees,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models EAGLE-2: Faster inference of language models with dynamic draft trees,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.068928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 343c301c-3e3d-45d1-80b2-3e1d6974f9be · outbound

This paper cites Eagle-3: Scaling up inference acceleration of large language models via training-time test,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Eagle-3: Scaling up inference acceleration of large language models via training-time test,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.061487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7b0a1622-72f0-44b1-8409-f9b8015de48a · outbound

This paper cites Adaserve: Accelerating multi-slo llm serving with slo-customized speculative decoding,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Adaserve: Accelerating multi-slo llm serving with slo-customized speculative decoding,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.756424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 541cab22-df40-40a4-9be6-1db16051545a · outbound

This paper cites Speculative decoding: Performance or illusion?.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Speculative decoding: Performance or illusion?

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.052560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ef9c02c0-d2bf-4737-bb93-dbf8600041bc · outbound

This paper cites CacheSlide: Unlocking cross Position-Aware KV cache reuse for accelerating LLM serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models CacheSlide: Unlocking cross Position-Aware KV cache reuse for accelerating LLM serving,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.045015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3460b5a7-58fa-4aa3-ad95-8654d9c6bff3 · outbound

This paper cites Agentix: An efficient serving engine for LLM agents as general programs,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Agentix: An efficient serving engine for LLM agents as general programs,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.036706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7650ec64-9a17-41cc-887e-007fdee0c498 · outbound

This paper cites No buffer, no bottleneck: Efficient Zero-Copy KV cache offloading for Long-Context LLMs,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models No buffer, no bottleneck: Efficient Zero-Copy KV cache offloading for Long-Context LLMs,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.029402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c00efa0f-bb4c-44b4-a9ea-f5bb1b31479f · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative inference and verification,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Specinfer: Accelerating large language model serving with tree-based speculative inference and verification,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.770410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3102521f-27a9-443d-aa13-b1c30c48ac49 · outbound

This paper cites Efficient large-scale language model training on gpu clusters using megatron-lm,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Efficient large-scale language model training on gpu clusters using megatron-lm,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.773049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cbac254-604b-47ce-bfb8-e22dd2af5948 · outbound

This paper cites CUDA Programming Guide: CUDA Graphs,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models CUDA Programming Guide: CUDA Graphs,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.020532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4c92c93e-63c6-4bb4-8c3f-29821dd13de7 · outbound

This paper cites NVIDIA Nsight Compute Documentation,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models NVIDIA Nsight Compute Documentation,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.012710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ad36ac27-bea9-41e2-a4f1-d6857fd8fe50 · outbound

This paper cites NVIDIA Nsight Systems User Guide,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models NVIDIA Nsight Systems User Guide,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:58.005213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74e51260-d55d-4a1d-95e1-14039000aba4 · outbound

This paper cites Marconi: Prefix caching for the era of hybrid llms,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Marconi: Prefix caching for the era of hybrid llms,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.998021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 52486329-8c91-4d4b-84bd-4b94310c1a63 · outbound

This paper cites Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.990529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 145fe7ed-7026-4bc8-a77f-92bca7747bd8 · outbound

This paper cites Qwen3.5: Towards native multimodal agents,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Qwen3.5: Towards native multimodal agents,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.982799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ed74e44a-f1bc-4d3d-a066-6b49d9fe8740 · outbound

This paper cites Get to the point: Summarization with pointer-generator networks,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Get to the point: Summarization with pointer-generator networks,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.974060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation adb0e956-5cf9-4cc3-b540-22e1d91385f2 · outbound

This paper cites GitHub - sgl-project/sglang at release/v0.5.12 — github.com,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models GitHub - sgl-project/sglang at release/v0.5.12 — github.com,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.965305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9eca6b96-d966-434e-b9cc-5227e861a25c · outbound

This paper cites anon8231489123/ShareGPT Vicuna unfiltered · Datasets at Hugging Face — huggingface.co,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models anon8231489123/ShareGPT Vicuna unfiltered · Datasets at Hugging Face — huggingface.co,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.956695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 27902834-7cb9-4369-9541-b26c00a13516 · outbound

This paper cites Llumnix: Dynamic scheduling for large language model serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Llumnix: Dynamic scheduling for large language model serving,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.948954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a5a3837-1995-4e42-b918-6191772cb2a2 · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.804544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74088bc6-074f-4dba-a5bf-651ef49861b7 · outbound

This paper cites Triton: an intermediate language and compiler for tiled neural network computations,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Triton: an intermediate language and compiler for tiled neural network computations,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.807486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f23af17-10ee-4ed3-ae8d-8f8dffa7159b · outbound

This paper cites Adap- tive draft sequence length: Enhancing speculative decoding throughput on pim-enabled systems,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Adap- tive draft sequence length: Enhancing speculative decoding throughput on pim-enabled systems,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.941600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9f2b2780-522c-4994-a2a1-e88fda4ec9ff · outbound

This paper cites Openhands: An open platform for ai software developers as generalist agents,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Openhands: An open platform for ai software developers as generalist agents,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.933584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 34f30b30-2b7c-4c4f-97c4-f776e3459680 · outbound

This paper cites Roofline: an insightful visual performance model for multicore architectures,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Roofline: an insightful visual performance model for multicore architectures,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.817103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22984f73-11fc-4377-bf95-5170c7303300 · outbound

This paper cites Stree: Speculative tree decoding for hybrid state space models,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Stree: Speculative tree decoding for hybrid state space models,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.924591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation defa3908-f307-47a4-8665-d722fd90f93b · outbound

This paper cites Strata: Hierarchical context caching for long context language model serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Strata: Hierarchical context caching for long context language model serving,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.915181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation da079084-1e09-4c0a-b498-92afe391c455 · outbound

This paper cites Gated delta networks: Improving mamba2 with delta rule,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Gated delta networks: Improving mamba2 with delta rule,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.906315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9febaefa-f8f9-4399-89a0-a73dc2045386 · outbound

This paper cites Deft: Decoding with flash tree-attention for efficient tree-structured llm inference,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Deft: Decoding with flash tree-attention for efficient tree-structured llm inference,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.896471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 37f2872d-6750-46d3-9319-69a66e55f7c5 · outbound

This paper cites Flashinfer: Efficient and customizable attention engine for llm inference serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Flashinfer: Efficient and customizable attention engine for llm inference serving,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.887251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 880a4d15-aa6e-4a15-9f48-a3ee80593255 · outbound

This paper cites Llmcompass: Enabling efficient hardware design for large language model inference,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Llmcompass: Enabling efficient hardware design for large language model inference,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.836278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd1f0d1-d306-4d0a-a222-e9585658d688 · outbound

This paper cites Swiftspec: Disaggregated speculative decoding and fused kernels for low-latency llm inference,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Swiftspec: Disaggregated speculative decoding and fused kernels for low-latency llm inference,

Reference 51

Resolution: metadata mismatch; raw_fallback, observed 2026-08-04T23:34:56.952275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fa610865-6a1f-44f2-800d-443f12480b41 · outbound

This paper cites Atom: Low-bit quantization for efficient and accurate llm serving,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Atom: Low-bit quantization for efficient and accurate llm serving,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.841217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4851dad1-8f2d-455d-be6b-1ab59ce296f0 · outbound

This paper cites Sglang: Efficient execution of structured language model programs,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Sglang: Efficient execution of structured language model programs,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.873171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b65ea5f1-7791-4bf5-bc26-0800be44c666 · outbound

This paper cites NanoFlow: Towards optimal large language model serving throughput,.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models NanoFlow: Towards optimal large language model serving throughput,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:57.862730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74e19205-6bed-40de-8329-6fe6d609e5ff · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:56.711032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers