thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

spec : remove check rate (#19377)

Browse source 
* spec: remove parameter spec-ngram-check-rate

* spec : renamed statistics vars

* spec : add n_call_begin, n_call_accept

* spec : don't enable key-map-stats
This commit is contained in:
Sascha Rogmann 2026-02-09 14:30:50 +01:00 • committed by GitHub
parent 81ddc60cb3
commit 292f6908cd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 36 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

13
docs/speculative.md
View file

@ -119,8 +119,6 @@ If a draft model is combined with a draftless decoding the draftless decoding ha
of lookup n-gram (default: 12)
--spec-ngram-size-m N ngram size M for ngram-simple/ngram-map speculative decoding, length
of draft m-gram (default: 48)
--spec-ngram-check-rate N ngram check rate for ngram-simple/ngram-map speculative decoding
(default: 1)
--spec-ngram-min-hits N minimum hits for ngram-map speculative decoding (default: 1)
```
@ -153,10 +151,6 @@ Sets the size M of the draft m-gram for n-gram map based speculative decoding.
The m-gram size determines how many tokens to draft when a match is found.
Larger values can provide more speedup but may reduce acceptance rate.
### `--spec-ngram-check-rate R`
This option aims at performance if the n-gram lookup in history is to costly. A lookup will be executed at every R tokens (default is 1, every token).
### `--spec-ngram-min-hits H`
This option defines how often a key has to appear in the token history to be used as a draft (default is 1).
@ -175,7 +169,12 @@ draft acceptance rate = 0.70312 ( 90 accepted / 128 generated)
statistics ngram_mod: #calls = 810, #gen drafts = 15, #acc drafts = 15, #gen tokens = 960, #acc tokens = 730, dur(b,g,a) = 0.149, 0.347, 0.005 ms
```
- `#calls`: number of calls of this implementations
```
statistics ngram_map_k: #calls(b,g,a) = 6 1690 26, #gen drafts = 26, #acc drafts = 26, #gen tokens = 1248, #acc tokens = 968, dur(b,g,a) = 2.234, 1.427, 0.016 ms
```
- `#calls(b,g,a)`: number of calls of begin (new prompt), generation and accumulation of this implementations
- `#gen drafts`: number of drafts generated by this implementation
- `#acc drafts`: number of drafts accepted (partially) by the main model
- `#gen tokens`: number of tokens generated by this implementation (including rejected tokens)