Skip to content

Add TQ2_0 quantization support to whisper.cpp #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Copilot wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

Add TQ2_0 quantization support to whisper.cpp #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
57b66d2
Initial plan
Copilot Jan 11, 2026
b62950d
Add TQ2_0 quantization support to whisper.cpp
Copilot Jan 11, 2026
c0f50e4
Add TQ2_0 to ggml_ftype_to_ggml_type mapping
Copilot Jan 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions examples/common-ggml.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ static const std::map<std::string, enum ggml_ftype> GGML_FTYPE_MAP = {
{"q4_k", GGML_FTYPE_MOSTLY_Q4_K},
{"q5_k", GGML_FTYPE_MOSTLY_Q5_K},
{"q6_k", GGML_FTYPE_MOSTLY_Q6_K},
{"tq2_0", GGML_FTYPE_MOSTLY_TQ2_0},
};

void ggml_print_ftypes(FILE * fp) {
Expand All @@ -24,7 +25,7 @@ void ggml_print_ftypes(FILE * fp) {

enum ggml_ftype ggml_parse_ftype(const char * str) {
enum ggml_ftype ftype;
if (str[0] == 'q') {
if (str[0] == 'q' || str[0] == 't') {
const auto it = GGML_FTYPE_MAP.find(str);
if (it == GGML_FTYPE_MAP.end()) {
fprintf(stderr, "%s: unknown ftype '%s'\n", __func__, str);
Expand Down Expand Up @@ -58,6 +59,7 @@ bool ggml_common_quantize_0(
case GGML_FTYPE_MOSTLY_Q4_K: qtype = GGML_TYPE_Q4_K; break;
case GGML_FTYPE_MOSTLY_Q5_K: qtype = GGML_TYPE_Q5_K; break;
case GGML_FTYPE_MOSTLY_Q6_K: qtype = GGML_TYPE_Q6_K; break;
case GGML_FTYPE_MOSTLY_TQ2_0: qtype = GGML_TYPE_TQ2_0; break;
case GGML_FTYPE_UNKNOWN:
case GGML_FTYPE_ALL_F32:
case GGML_FTYPE_MOSTLY_F16:
Expand Down Expand Up @@ -188,6 +190,7 @@ bool ggml_common_quantize_0(
case GGML_TYPE_Q4_K:
case GGML_TYPE_Q5_K:
case GGML_TYPE_Q6_K:
case GGML_TYPE_TQ2_0:
{
cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], nullptr);
} break;
Expand All @@ -211,7 +214,6 @@ bool ggml_common_quantize_0(
case GGML_TYPE_IQ1_M:
case GGML_TYPE_BF16:
case GGML_TYPE_TQ1_0:
case GGML_TYPE_TQ2_0:
case GGML_TYPE_MXFP4:
case GGML_TYPE_COUNT:
{
Expand Down
1 change: 1 addition & 0 deletions ggml/include/ggml.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -458,6 +458,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ1_M = 23, // except 1d tensors
GGML_FTYPE_MOSTLY_BF16 = 24, // except 1d tensors
GGML_FTYPE_MOSTLY_MXFP4 = 25, // except 1d tensors
GGML_FTYPE_MOSTLY_TQ2_0 = 26, // except 1d tensors
};

// available tensor operations:
Expand Down
1 change: 1 addition & 0 deletions ggml/src/ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1377,6 +1377,7 @@ enum ggml_type ggml_ftype_to_ggml_type(enum ggml_ftype ftype) {
case GGML_FTYPE_MOSTLY_IQ4_XS: wtype = GGML_TYPE_IQ4_XS; break;
case GGML_FTYPE_MOSTLY_IQ3_S: wtype = GGML_TYPE_IQ3_S; break;
case GGML_FTYPE_MOSTLY_IQ2_S: wtype = GGML_TYPE_IQ2_S; break;
case GGML_FTYPE_MOSTLY_TQ2_0: wtype = GGML_TYPE_TQ2_0; break;
case GGML_FTYPE_UNKNOWN: wtype = GGML_TYPE_COUNT; break;
case GGML_FTYPE_MOSTLY_Q4_1_SOME_F16: wtype = GGML_TYPE_COUNT; break;
}
Expand Down