SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.00264 · 2024

Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 12 failures of our instrument; 2 no recorded run); 2 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.00264.json · badge: /api/ran/2408.00264.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
XiaoBin1992/clover community (classifier label)
classifier basis not recorded on the link
15 ran · 2 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/modeling_eagle.py
code served (permissive licence) · get_code("30d7eec482ebf6b1")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:09:20Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a tensor with shape (batch, num_key_value_heads, seqlen, head_dim)
# Using distinct sizes: batch=2, num_key_value_heads=3, seqlen=5, head_dim=4
hidden_states = torch.randn(2, 3, 5, 4)

# n_rep is the repetition factor
n_rep = 2

ARGS = {
    "hidden_states": hidden_states,
    "n_rep": n_rep,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) — shape (2, 6, 5, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/model/clover2.py
code served (permissive licence) · get_code("3c76e52815c5401d")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:23:17Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with shape (batch, num_key_value_heads, seqlen, head_dim)
# Using distinct sizes: batch=2, num_key_value_heads=3, seqlen=5, head_dim=4
hidden_states = torch.randn(2, 3, 5, 4)

# n_rep is the repetition factor
n_rep = 2

ARGS = {
    "hidden_states": hidden_states,
    "n_rep": n_rep,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) — shape (2, 6, 5, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/model/modeling_mixtral_kv.py
code served (permissive licence) · get_code("d61c483a3c2b3156")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct tiny tensors for the function
batch_size = 2
seq_len = 3
num_heads = 4
head_dim = 8

# Query and key tensors: [batch_size, num_heads, seq_len, head_dim]
q = torch.randn(batch_size, num_heads, seq_len, head_dim)
k = torch.randn(batch_size, num_heads, seq_len, head_dim)

# Cosine and sine embeddings: [seq_len, head_dim]
# These will be indexed by position_ids
cos = torch.randn(seq_len, head_dim)
sin = torch.randn(seq_len, head_dim)

# Position IDs: [batch_size, seq_len]
position_ids = torch.tensor([[0, 1, 2], [0, 1, 2]], dtype=torch.long)

# unsqueeze_dim parameter
unsqueeze_dim = 1

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
    "unsqueeze_dim": unsqueeze_dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/modeling_eagle.py
code served (permissive licence) · get_code("f725bc2d76076485")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for q and k
# Shape: (batch_size=2, seq_len=3, hidden_dim=4)
q = torch.randn(2, 3, 4)
k = torch.randn(2, 3, 4)

# Create cos and sin tensors
# The function squeezes dimensions 1 and 0, then indexes by position_ids
# So we need shape that allows this: (1, 1, seq_len, hidden_dim)
cos = torch.randn(1, 1, 5, 4)
sin = torch.randn(1, 1, 5, 4)

# Create position_ids
# Shape: (batch_size=2, seq_len=3)
position_ids = torch.tensor([[0, 1, 2], [1, 2, 3]])

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/model/clover2.py
code served (permissive licence) · get_code("9a65a30d006fc96e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyze the function:
# - q: tensor, used with *, rotate_half, and arithmetic ops
# - k: tensor, used with *, rotate_half, and arithmetic ops
# - cos: tensor, squeezed twice on dims 1 and 0, indexed by position_ids, unsqueezed
# - sin: tensor, squeezed twice on dims 1 and 0, indexed by position_ids, unsqueezed
# - position_ids: tensor, used to index into cos and sin

# The function expects:
# - q and k to have shape compatible with rotate_half (last dim must be even)
# - cos and sin to have shape (seq_len, 1, hidden_dim) before squeezing
# - position_ids to be indices into the sequence dimension

batch_size = 2
seq_len = 3
hidden_dim = 4
num_positions = 5

# q and k: (batch, seq_len, hidden_dim)
q = torch.randn(batch_size, seq_len, hidden_dim)
k = torch.randn(batch_size, seq_len, hidden_dim)

# cos and sin: (num_positions, 1, hidden_dim)
# After squeeze(1).squeeze(0), they become (num_positions, hidden_dim)
cos = torch.randn(num_positions, 1, hidden_dim)
sin = torch.randn(num_positions, 1, hidden_dim)

# position_ids: indices into the position dimension, shape (batch, seq_len)
position_ids = torch.tensor([[0, 1, 2], [1, 2, 3]], dtype=torch.long)

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_tree_buffers Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/model/utils_alpha.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("8a738587f4d897b9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

initialize_past_key_values Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/model/kv_cache.py
code served (permissive licence) · get_code("aadc9c83d7ec2701")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.num_hidden_layers = 2
        self.num_key_value_heads = 3
        self.max_position_embeddings = 8
        self.hidden_size = 12
        self.num_attention_heads = 4

class MockAttention(nn.Module):
    def __init__(self):
        super().__init__()
        self.q_proj = nn.Linear(12, 12)

class MockLayer(nn.Module):
    def __init__(self):
        super().__init__()
        self.self_attn = MockAttention()

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.config = MockConfig()
        self.model = nn.Module()
        self.model.layers = nn.ModuleList([MockLayer() for _ in range(self.config.num_hidden_layers)])
        self.dtype = torch.float32

model = MockModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pad_path Ran
ran, violated the contract we drafted
XiaoBin1992/clover/clover/model/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("a40c43d3dbc369d3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepare_logits_processor Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/model/utils_alpha.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("f02fecb5f780c3f8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepare_logits_processor Ran
ran on a synthesized input
XiaoBin1992/clover/clover/model/utils.py
code served (permissive licence) · get_code("fdb811155913ebca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned LogitsProcessorList. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from transformers.generation.logits_process import LogitsProcessorList, RepetitionPenaltyLogitsProcessor, TemperatureLogitsWarper, TopKLogitsWarper, TopPLogitsWarper

torch.manual_seed(0)

# The function prepare_logits_processor takes 4 float/int parameters
# and returns a LogitsProcessorList based on their values.
# No complex objects are actually used by the function body.

ARGS = {
    "temperature": 0.9,
    "repetition_penalty": 1.2,
    "top_p": 0.95,
    "top_k": 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LogitsProcessorList — a LogitsProcessorList output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LogitsProcessorList output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
XiaoBin1992/clover/clover/model/modeling_llama_kv.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("f6e0c0fc3868b787")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rotate_half Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/modeling_eagle.py
code served (permissive licence) · get_code("b99eea6376d1e212")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function rotate_half takes a single parameter 'x' which is a tensor
# It accesses x.shape[-1] to get the last dimension
# It uses indexing with [..., :] slicing notation
# It calls torch.cat() to concatenate tensors

# Create a small tensor with shape (2, 4) - batch size 2, hidden dim 4
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rotate_half Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/model/clover2.py
code served (permissive licence) · get_code("e03d53ba9d4f9ae5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function takes a single parameter 'x' which is a tensor
# It accesses x[..., :x.shape[-1] // 2] and x[..., x.shape[-1] // 2:]
# So x needs to be a tensor with a last dimension that can be split in half
# Let's create a small tensor with batch size 2 and feature dimension 4

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rotate_half Ran
ran; our contract draft was wrong, not the code
XiaoBin1992/clover/clover/model/modeling_llama_kv.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("b71b0ed70aa2939c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

timer Ran
ran on a synthesized input
XiaoBin1992/clover/clover/model/utils.py
code served (permissive licence) · get_code("b54951ffbd7a4fc0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import time

def timer(func):
    def wrapper(*args, **kwargs):
        torch.cuda.synchronize()
        start = time.perf_counter()
        result = func(*args, **kwargs)
        torch.cuda.synchronize()
        elapsed = time.perf_counter() - start
        print(f'{func.__name__} took {elapsed} seconds')
        return result
    return wrapper

# Create a simple test function to be decorated
@timer
def sample_computation(x, y):
    return x + y

torch.manual_seed(0)

# Define arguments for the timer function
# The timer function takes a single parameter: func (a callable)
ARGS = {
    'func': sample_computation
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
apply_rotary_pos_emb Not yet run
unverified (harvested, no recorded run)
XiaoBin1992/clover/clover/model/modeling_llama_kv.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SAI-Lab-NYU/DREAM-S, is pointer only (licence: NONE) · get_code("bad260f6d71db00c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SAI-Lab-NYU/DREAM-S, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_balancing_loss_func Not yet run
unverified (harvested, no recorded run)
XiaoBin1992/clover/clover/model/modeling_mixtral_kv.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ShayekhBinIslam/openrag, is pointer only (licence: CC-BY-4.0) · get_code("d9308d9bf18cd072")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ShayekhBinIslam/openrag, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 4 the same month, 9 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
rotate_half 360 other papers
170 dated earlier, 7 the same month, 174 later, 6 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
105 dated earlier, 8 the same month, 126 later, 2 same year, order not determinable, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb 83 other papers
51 dated earlier, 3 the same month, 27 later, 2 same year, order not determinable · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
apply_rotary_pos_emb 75 other papers
40 dated earlier, 1 the same month, 34 later · 2 only as an assembly brick
2309.11499 (2023-09)
DreamLLM: Synergistic Multimodal Comprehension and Creation
2312.02051 (2023-12)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
2312.03414 (2023-12)
Compressed Context Memory For Online Language Model Interaction
and 72 more not named here
load_balancing_loss_func 7 other papers
2 dated earlier, 5 later
2310.11511 (2023-10)
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
2405.13845 (2024-05)
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
2507.22424 (2025-07)
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
and 4 more not named here
pad_path 4 other papers
4 later
2503.10135 (2025-03)
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
2601.15498 (2026-01)
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification
2602.16052 (2026-02)
MoE-Spec: Expert Budgeting for Efficient Speculative Decoding
and 1 more not named here
initialize_past_key_values 2 other papers
2 later
2410.06916 (2024-10)
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
2503.10135 (2025-03)
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
generate_tree_buffers 1 other paper
1 later
2606.00535 (2026-06)
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
prepare_logits_processor 1 other paper
1 later
2606.00535 (2026-06)
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) frequently suffer from inefficiencies, largely attributable to the discord between the requirements of auto-regressive decoding and the architecture of contemporary GPUs. Recently, regressive lightweight speculative decoding has garnered attention for its notable efficiency improvements in text generation tasks. This approach utilizes a lightweight regressive draft model, like a Recurrent Neural Network (RNN) or a single transformer decoder layer, leveraging sequential information to iteratively predict potential tokens. Specifically, RNN draft models are computationally economical but tend to deliver lower accuracy, while attention decoder layer models exhibit the opposite traits. This paper presents Clover-2, an advanced iteration of Clover, an RNN-based draft model designed to achieve comparable accuracy to that of attention decoder layer models while maintaining minimal computational overhead. Clover-2 enhances the model architecture and incorporates knowledge distillation to increase Clover's accuracy and improve overall efficiency. We conducted experiments using the open-source Vicuna 7B and LLaMA3-Instruct 8B models. The results demonstrate that Clover-2 surpasses existing methods across various model architectures, showcasing its efficacy and robustness.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.00264")
get_code_for_paper("2408.00264")
have("2408.00264")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.00264.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.00264.svg)](https://syntology.ai/paper/2408.00264)

Connect an agent — have() is free.