mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

model : support Step3.5-Flash (#19283)

Browse Source 
* Support Step3.5-Flash

* fix: norm.weight + 1 (HF zero_centered=true)

* step35: simplify GGUF conversion + drop redundant rope KVs

* Address review feedback

* rename limits -> clamp

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Apply suggestion from @CISC

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* rename swiglu limits -> swiglu clamp in LLM_KV

* avoid CI fail

* Apply suggestions from code review

* Apply suggestions from code review

* disabled KV shifting for LLM_ARCH_STEP35

* Apply suggestions from code review

* mistakenly removed cmath

* add model size && apply missed suggestion

* assert partial_rotary_factors

* fix CI errors:

* load freq_base_swa

---------

Co-authored-by: lvyichen <lvyichen@stepfun.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
forforever73
2026-02-07 04:06:14 +08:00
committed by GitHub
parent 3228e77287
commit b83111815e
15 changed files with 576 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache-iswa.cpp
+3 -1
View File
@@ -218,7 +218,9 @@ llama_memory_context_ptr llama_kv_cache_iswa::init_update(llama_context * lctx,
}
bool llama_kv_cache_iswa::get_can_shift() const {
return kv_base->get_size() == kv_swa->get_size();
return kv_base->get_can_shift() &&
kv_swa->get_can_shift() &&
kv_base->get_size() == kv_swa->get_size();
}
void llama_kv_cache_iswa::state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const {